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

    Neuronpedia

    INDEX
    Explanations

    bracket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    озвращает
    -0.07
    يست
    -0.07
     hecho
    -0.07
     tune
    -0.06
    TM
    -0.06
    mpeg
    -0.06
     Nhân
    -0.06
    怕
    -0.06
    isto
    -0.06
    Found
    -0.06
    POSITIVE LOGITS
    ~-~-~-~-
    0.08
    였
    0.07
    言われ
    0.07
     paed
    0.07
    (ph
    0.06
    _nullable
    0.06
    üssen
    0.06
     Dis
    0.06
    🌶
    0.06
     weakening
    0.06
    Act Density 0.018%

    No Known Activations