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

    Neuronpedia

    INDEX
    Explanations

    thank you so much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ຄວ
    0.88
    rogate
    0.69
    uera
    0.69
     vài
    0.67
    стоя
    0.67
     occasional
    0.64
    திரு
    0.64
     unorthodox
    0.63
     облі
    0.62
    anor
    0.62
    POSITIVE LOGITS
     класс
    0.79
     amable
    0.78
     kindly
    0.75
     gummies
    0.74
    ॉम
    0.73
     alojamiento
    0.73
     답변
    0.72
     hospitality
    0.72
     じゃん
    0.72
     स्पिन
    0.71
    Act Density 0.006%

    No Known Activations