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

    Neuronpedia

    INDEX
    Explanations

    /blob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HOST
    -0.07
    Modal
    -0.07
    .master
    -0.07
    _WINDOW
    -0.06
    _window
    -0.06
    .flatten
    -0.06
     해당
    -0.06
     decoding
    -0.06
     Tower
    -0.06
     Az
    -0.06
    POSITIVE LOGITS
    ILD
    0.07
    бы
    0.07
    خي
    0.06
    ố
    0.06
    Người
    0.06
    лев
    0.06
    ристи
    0.06
     açı
    0.06
     chlorine
    0.06
    寻
    0.06
    Act Density 0.002%

    No Known Activations