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

    Neuronpedia

    INDEX
    Explanations

    words that emphasize importance or offer warnings

    oai_token-act-pair · gemini-2.0-flash

    important considerations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expect
    -0.56
    expect
    -0.54
    SOUNDBITE
    -0.52
    labelledby
    -0.49
    tand
    -0.48
    __((
    -0.47
    NameInMap
    -0.43
    のだろうか
    -0.43
    бли
    -0.43
    laufen
    -0.43
    POSITIVE LOGITS
     to
    0.79
     fallu
    0.67
     pitä
    0.64
     muſt
    0.63
     שוליים
    0.62
     للاسماء
    0.61
     treba
    0.61
    ต้อง
    0.61
     MotionEvent
    0.60
     phải
    0.60
    Act Density 1.428%

    No Known Activations