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

    Neuronpedia

    INDEX
    Explanations

    Suffixes of origin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    넗
    -0.08
    Cell
    -0.07
    Ju
    -0.07
     viet
    -0.07
     id
    -0.07
    来进行
    -0.07
    ᴈ
    -0.07
    可见
    -0.06
     없다
    -0.06
    _five
    -0.06
    POSITIVE LOGITS
    面粉
    0.07
    吃饭
    0.07
    哥们
    0.07
    磕
    0.07
     VARIANT
    0.07
    heits
    0.07
     кон
    0.07
    ;"
    0.07
     "`
    0.07
    抡
    0.07
    Act Density 0.029%

    No Known Activations