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

    Neuronpedia

    INDEX
    Explanations

    hot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accus
    -0.08
    роиз
    -0.07
    اذا
    -0.07
    もし
    -0.06
     Testament
    -0.06
    encias
    -0.06
    بو
    -0.06
    annotate
    -0.06
     Rooms
    -0.06
    될
    -0.06
    POSITIVE LOGITS
     milyon
    0.07
     instantiation
    0.06
    ifferential
    0.06
    _err
    0.06
     xác
    0.06
    758
    0.06
     attribution
    0.06
     чемпіон
    0.06
    hamster
    0.06
    ặp
    0.06
    Act Density 0.000%

    No Known Activations