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
    ｢
    -0.07
     Lawyers
    -0.06
    ’’
    -0.06
    individual
    -0.06
    Якщо
    -0.06
    serial
    -0.06
     $("
    -0.06
    (Group
    -0.06
    (redis
    -0.06
    .fb
    -0.06
    POSITIVE LOGITS
     MOZ
    0.07
     HELP
    0.07
    \Database
    0.06
    ύ
    0.06
     SENT
    0.06
    jured
    0.06
    uggling
    0.06
     �
    0.06
     declar
    0.06
     ром
    0.06
    Act Density 0.007%

    No Known Activations