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

    Neuronpedia

    INDEX
    Explanations

    asterisk symbol

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的身影
    -0.07
     празд
    -0.07
     patriarch
    -0.07
    散发着
    -0.07
    体育馆
    -0.07
     Chairs
    -0.07
     magnetic
    -0.07
     monuments
    -0.06
     إطلاق
    -0.06
    ./
    -0.06
    POSITIVE LOGITS
    arriv
    0.08
    𝙻
    0.08
    овор
    0.07
    宜
    0.07
     trời
    0.07
     regulated
    0.07
    ов
    0.07
    ollapsed
    0.07
    /U
    0.07
     imagery
    0.07
    Act Density 0.003%

    No Known Activations