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

    Neuronpedia

    INDEX
    Explanations

    Stack Exchange sites

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SCALE
    -0.08
    类
    -0.07
    ///↵↵
    -0.06
    므로
    -0.06
    (tmp
    -0.06
    %;
↵
    -0.06
     psychosis
    -0.06
    SCALE
    -0.06
    aných
    -0.06
     harbour
    -0.06
    POSITIVE LOGITS
     Wel
    0.07
     chua
    0.07
     nh
    0.06
     chez
    0.06
     dispatched
    0.06
    ,args
    0.06
     Alicia
    0.06
     cess
    0.06
     Чер
    0.06
     Ma
    0.06
    Act Density 0.012%

    No Known Activations