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

    Neuronpedia

    INDEX
    Explanations

    if and only if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.98
    ور
    0.93
    g
    0.85
    스
    0.83
    ન
    0.81
    ల
    0.80
    د
    0.79
    ri
    0.78
     entreprises
    0.76
    هم
    0.75
    POSITIVE LOGITS
     Superman
    0.63
    ↵
    0.62
     था
    0.58
    TimeSeries
    0.58
     wtedy
    0.58
    jeti
    0.57
    ί
    0.56
    PhysRev
    0.55
     That
    0.54
     تعداد
    0.54
    Act Density 0.000%

    No Known Activations