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

    Neuronpedia

    INDEX
    Explanations

    form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    にかく
    0.87
     mikt
    0.85
     far
    0.85
    消化
    0.83
    水平
    0.83
    版
    0.79
     hàng
    0.78
     زن
    0.78
     levels
    0.76
    s
    0.76
    POSITIVE LOGITS
    ulates
    1.41
    ulate
    1.22
    ulators
    1.08
    ulação
    1.03
     geométricas
    1.02
    ulations
    0.94
    ulator
    0.93
    ulated
    0.91
     Shui
    0.91
    ulas
    0.90
    Act Density 0.316%

    No Known Activations