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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unlimited
    -0.07
     inclined
    -0.07
     peanuts
    -0.06
     Replies
    -0.06
    .dialog
    -0.06
    .alias
    -0.06
     نشده
    -0.06
    าณ
    -0.06
    ütün
    -0.06
     marty
    -0.06
    POSITIVE LOGITS
    (orig
    0.06
    �
    0.06
    _pg
    0.06
     fille
    0.06
    (photo
    0.06
     ב
    0.06
    PTR
    0.06
     glGet
    0.06
     شماره
    0.06
    백
    0.06
    Act Density 0.012%

    No Known Activations