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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IDEO
    -0.07
    加剧
    -0.07
    alin
    -0.07
    (heap
    -0.07
    During
    -0.07
    (conv
    -0.07
    涂
    -0.07
    _VOID
    -0.07
    (ERROR
    -0.06
    .booking
    -0.06
    POSITIVE LOGITS
    ǵ
    0.07
    发展战略
    0.07
    禔
    0.07
    straints
    0.07
     Analyzer
    0.07
     większe
    0.07
    herited
    0.06
    稱
    0.06
    /site
    0.06
    汉子
    0.06
    Act Density 0.038%

    No Known Activations