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

    Neuronpedia

    INDEX
    Explanations

    engine as power source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    1.06
    ле
    0.80
     are
    0.79
    েন
    0.77
    ामध्ये
    0.75
    ında
    0.74
    летов
    0.73
    行う
    0.72
    edes
    0.70
    '
    0.69
    POSITIVE LOGITS
    a
    0.94
    ה
    0.90
    ش
    0.89
    ه
    0.84
    ل
    0.81
     engine
    0.77
    خواست
    0.75
    ਸ
    0.73
    پ
    0.72
    0
    0.71
    Act Density 0.009%

    No Known Activations