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

    Neuronpedia

    INDEX
    Explanations

    Code/version information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ď
    -0.08
    ستر
    -0.07
     الفرص
    -0.07
    مين
    -0.07
    .Change
    -0.06
    ún
    -0.06
    魈
    -0.06
     Gregg
    -0.06
    "default
    -0.06
    .Dense
    -0.06
    POSITIVE LOGITS
    (',',$
    0.07
     bracelets
    0.07
     fiyatı
    0.07
     bron
    0.07
    _REFERER
    0.07
     unbelie
    0.07
     eigen
    0.07
    腹部
    0.06
    营业额
    0.06
    (ex
    0.06
    Act Density 0.049%

    No Known Activations