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

    Neuronpedia

    INDEX
    Explanations

    derivatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .plugins
    -0.07
     interacting
    -0.06
    .transactions
    -0.06
    px
    -0.06
    _scores
    -0.06
     imposition
    -0.06
    -image
    -0.06
    olygon
    -0.06
    合
    -0.06
    ===========
    -0.06
    POSITIVE LOGITS
    "]↵↵
    0.07
     сопров
    0.07
    로운
    0.07
    Recovered
    0.07
     pornô
    0.06
    SECTION
    0.06
    ')])↵
    0.06
     输
    0.06
     teste
    0.06
     sesso
    0.06
    Act Density 0.004%

    No Known Activations