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

    Neuronpedia

    INDEX
    Explanations

    path

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     genres
    -0.08
    Ｄ
    -0.07
    Z
    -0.07
     Silicon
    -0.07
     G
    -0.07
     Verizon
    -0.07
    刃
    -0.07
     M
    -0.06
    谌
    -0.06
     subtitle
    -0.06
    POSITIVE LOGITS
    AILABLE
    0.07
    .Magic
    0.07
     haired
    0.07
    %'
    0.07
     salvar
    0.07
    _Current
    0.07
    want
    0.07
    ्
    0.06
    lıkl
    0.06
    럴
    0.06
    Act Density 0.000%

    No Known Activations