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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     periods
    -0.07
    anı
    -0.06
    _endpoint
    -0.06
    eb
    -0.06
    Coordinates
    -0.06
     Weiner
    -0.06
     Pollution
    -0.06
    para
    -0.06
    ookeeper
    -0.06
    unning
    -0.06
    POSITIVE LOGITS
    &&(
    0.06
     thừa
    0.06
    Card
    0.06
    /master
    0.06
     �
    0.06
     ritual
    0.06
     gorge
    0.06
    真
    0.06
    incy
    0.06
     filles
    0.06
    Act Density 0.002%

    No Known Activations