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

    Neuronpedia

    INDEX
    Explanations

    build

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    קב
    -0.07
    冈
    -0.07
    _LEAVE
    -0.07
    _crypto
    -0.07
    �
    -0.07
     bağlantı
    -0.07
     ITV
    -0.07
     europe
    -0.07
    シア
    -0.07
    cn
    -0.07
    POSITIVE LOGITS
    .configure
    0.07
    0.07
    做了
    0.07
    ,String
    0.07
     Rod
    0.07
    姐
    0.07
    .annotation
    0.07
     sister
    0.07
    家庭教育
    0.07
    ///
    0.07
    Act Density 0.002%

    No Known Activations