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

    Neuronpedia

    INDEX
    Explanations

    rgb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Đối
    -0.07
     rozvoj
    -0.07
    十六
    -0.06
    ‘
    -0.06
    .get
    -0.06
     imposing
    -0.06
    urv
    -0.06
     ◑
    -0.06
     kot
    -0.06
    لل
    -0.06
    POSITIVE LOGITS
    .Constant
    0.07
     olmadığı
    0.07
    äre
    0.07
    ,std
    0.07
     paycheck
    0.06
     emph
    0.06
    843
    0.06
    _else
    0.06
     tainted
    0.06
     ổ
    0.06
    Act Density 0.001%

    No Known Activations