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

    Neuronpedia

    INDEX
    Explanations

    engines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MAP
    -0.07
     Bucks
    -0.06
    Message
    -0.06
    =p
    -0.06
    简单
    -0.06
     Ru
    -0.06
    anno
    -0.06
    .Provider
    -0.06
     annoyed
    -0.06
    отов
    -0.06
    POSITIVE LOGITS
    /www
    0.07
    ــــ
    0.06
    ạo
    0.06
     dll
    0.06
     exe
    0.06
    ‰
    0.06
    _registro
    0.06
    ้ไข
    0.06
     {?}
    0.06
    .Fatal
    0.06
    Act Density 0.207%

    No Known Activations