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

    Neuronpedia

    INDEX
    Explanations

    Colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _quiz
    -0.07
     документов
    -0.07
    屁
    -0.07
     foreign
    -0.07
     scoff
    -0.07
    支线任务
    -0.07
     così
    -0.07
    冲刺
    -0.07
     điểm
    -0.07
     mưa
    -0.07
    POSITIVE LOGITS
    (bean
    0.07
    🍸
    0.07
    不同的
    0.07
    鼓舞
    0.07
    held
    0.07
    ﺑ
    0.06
     düzen
    0.06
     üst
    0.06
    [U
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations