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

    Neuronpedia

    INDEX
    Explanations

    #include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    聽
    -0.07
     =================================================
    -0.06
    EM
    -0.06
    تیب
    -0.06
    ريب
    -0.06
     wreck
    -0.06
    اطق
    -0.06
     "**
    -0.06
    _USERNAME
    -0.06
    ัน
    -0.06
    POSITIVE LOGITS
     incidence
    0.07
    选择
    0.07
    alarında
    0.06
     productList
    0.06
    'Neill
    0.06
    少女
    0.06
    キング
    0.06
    ]|[
    0.06
    創
    0.06
    �
    0.06
    Act Density 0.009%

    No Known Activations