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

    Neuronpedia

    INDEX
    Explanations

    dragging through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     परस्मैपदी
    0.42
    ීමට
    0.41
     عليهم
    0.39
     armament
    0.39
    靂
    0.39
     comunicar
    0.38
     চাপে
    0.38
    馭
    0.38
     cerebral
    0.38
    ээр
    0.37
    POSITIVE LOGITS
    drag
    0.67
     drag
    0.64
     dragged
    0.64
     Drag
    0.62
    拖
    0.61
     dragging
    0.56
     drags
    0.54
    Dragged
    0.53
    Drag
    0.50
    dragging
    0.46
    Act Density 0.051%

    No Known Activations