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

    Neuronpedia

    INDEX
    Explanations

    Testing and exams

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    antt
    -0.08
    _INTER
    -0.07
    Các
    -0.07
    INARY
    -0.06
    상
    -0.06
     Giá
    -0.06
    channel
    -0.06
    ющий
    -0.06
     JPEG
    -0.06
    دری
    -0.06
    POSITIVE LOGITS
     sürdür
    0.07
    \Core
    0.06
     {{--<
    0.06
     Overnight
    0.06
     incomes
    0.06
    pegawai
    0.06
     overcome
    0.06
    .policy
    0.06
     �
    0.06
     returning
    0.06
    Act Density 0.055%

    No Known Activations