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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ué
    -0.07
    理由
    -0.07
    滚滚
    -0.07
    ilen
    -0.07
    prix
    -0.07
    冲突
    -0.07
    江湖
    -0.07
    lijah
    -0.07
     situation
    -0.07
    poon
    -0.07
    POSITIVE LOGITS
    WindowTitle
    0.08
    VT
    0.07
    _VARS
    0.07
    BYTE
    0.07
    新浪微博
    0.07
    ++];↵
    0.07
     HOUSE
    0.06
    IALIZ
    0.06
    Specifier
    0.06
    _callback
    0.06
    Act Density 0.009%

    No Known Activations