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

    Neuronpedia

    INDEX
    Explanations

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Еще
    0.96
     Сайт
    0.96
     وعلى
    0.92
    iendo
    0.92
    iin
    0.91
     Среди
    0.91
    י
    0.89
    iere
    0.89
    ió
    0.88
    ሳሪያ
    0.88
    POSITIVE LOGITS
    ડ
    0.86
    ସ
    0.84
    హ
    0.79
    >
    0.79
    高さ
    0.78
     bristles
    0.76
    ிலிருந்து
    0.75
    のア
    0.73
     igu
    0.72
    畢
    0.70
    Act Density 0.095%

    No Known Activations