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

    Neuronpedia

    INDEX
    Explanations

    offering choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     youths
    0.75
    责任
    0.68
     पार्श्व
    0.67
     girls
    0.66
    嗪
    0.65
     youth
    0.65
     varia
    0.64
     забо
    0.63
     varies
    0.63
    bres
    0.63
    POSITIVE LOGITS
    スケ
    0.70
     Tamaño
    0.68
    SIZE
    0.66
     आइट
    0.66
    начала
    0.66
     énergétique
    0.64
    arette
    0.64
    Humidity
    0.63
     ukuran
    0.62
    дони
    0.62
    Act Density 0.018%

    No Known Activations