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

    Neuronpedia

    INDEX
    Explanations

    firm surface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ill
    0.69
    all
    0.68
    im
    0.67
    ش
    0.66
    p
    0.63
    1
    0.62
    he
    0.61
    a
    0.61
    ang
    0.60
    as
    0.59
    POSITIVE LOGITS
    NumberOperation
    0.59
    ExecutionContext
    0.49
    UserNotification
    0.46
    <0x19>
    0.46
    维生素
    0.46
    InsertInt
    0.45
     înd
    0.45
    ==(
    0.45
    RequestContext
    0.45
    VideoCapture
    0.44
    Act Density 0.000%

    No Known Activations