Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code syntax elements such as brackets and semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets ending with punctuation

    np_acts-logits-general · gemini-2.0-flash

    closing bracket or parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.67
    /
    -0.63
     
    -0.60
    <bos>
    -0.59
     and
    -0.59
    ,
    -0.54
     &
    -0.53
       
    -0.53
     colspan
    -0.52
    isi
    -0.51
    POSITIVE LOGITS
    1.06
     ―――――
    0.75
     AspNetCore
    0.74
     RSSSF
    0.73
    Przypisy
    0.73
    =$?
    0.73
    帖最后由
    0.71
     ――――――――
    0.70
    triangleq
    0.69
     noqa
    0.68
    Act Density 0.070%

    No Known Activations