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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     firefighters
    -0.07
    (props
    -0.06
     delivered
    -0.06
     LOWER
    -0.06
    _TCP
    -0.06
    Sequential
    -0.06
    moire
    -0.05
    Vertices
    -0.05
    <View
    -0.05
    约
    -0.05
    POSITIVE LOGITS
    ='.
    0.08
    тов
    0.07
     itm
    0.07
    'value
    0.07
     ساخت
    0.07
     ”
    0.06
     spirit
    0.06
     unnatural
    0.06
    :v
    0.06
    ,"\
    0.06
    Act Density 0.036%

    No Known Activations