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

    Neuronpedia

    INDEX
    Explanations

    Random facts and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тап
    -0.07
    くだ
    -0.07
    openid
    -0.07
    puty
    -0.06
     чор
    -0.06
    Tok
    -0.06
     concatenated
    -0.06
     Horny
    -0.06
    Unary
    -0.06
    یلی
    -0.06
    POSITIVE LOGITS
    ltra
    0.07
     Merchant
    0.07
     fikir
    0.06
     Brasil
    0.06
    *num
    0.06
     Eis
    0.06
     phê
    0.06
     Row
    0.06
    .TIME
    0.06
    BufferSize
    0.06
    Act Density 0.270%

    No Known Activations