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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    驚
    -0.08
    Sometimes
    -0.08
    ائج
    -0.07
     mockery
    -0.07
     komt
    -0.07
    _box
    -0.06
    iqueta
    -0.06
    惊
    -0.06
     kä
    -0.06
     reward
    -0.06
    POSITIVE LOGITS
    902
    0.07
    TriState
    0.06
    getRepository
    0.06
     supernatural
    0.06
     ổn
    0.06
    .Offset
    0.06
     Мас
    0.06
    ulsion
    0.06
    utherland
    0.06
    .interfaces
    0.06
    Act Density 0.001%

    No Known Activations