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

    Neuronpedia

    INDEX
    Explanations

    code completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     భాగ
    0.86
     angust
    0.86
     perspective
    0.85
     생각을
    0.83
     naissance
    0.82
     بیشتری
    0.82
     nacimiento
    0.80
    isés
    0.80
     è
    0.78
    São
    0.78
    POSITIVE LOGITS
    示例
    0.87
    ቬ
    0.85
    整形
    0.81
     optimal
    0.80
    tır
    0.79
    您的
    0.79
     Ihres
    0.79
    具体
    0.79
    रां
    0.78
    ാൻ
    0.77
    Act Density 0.000%

    No Known Activations