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

    Neuronpedia

    INDEX
    Explanations

    "//"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Leah
    -0.07
    _market
    -0.06
     Margaret
    -0.06
     dolls
    -0.06
    _spot
    -0.06
    _corpus
    -0.06
    037
    -0.06
    чини
    -0.06
     Ginny
    -0.06
    ith
    -0.06
    POSITIVE LOGITS
     같
    0.08
     方法
    0.07
     heck
    0.07
    _tt
    0.07
     Align
    0.07
     كيف
    0.06
    ��
    0.06
    .every
    0.06
    accessToken
    0.06
    �
    0.06
    Act Density 0.009%

    No Known Activations