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

    Neuronpedia

    INDEX
    Explanations

    actual followed by outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    2.55
    ir
    1.88
    im
    1.87
     ♪
    1.73
     φ
    1.73
     Snapchat
    1.63
     Webinar
    1.57
     ♡
    1.54
     ×
    1.52
    phi
    1.50
    POSITIVE LOGITS
    стью
    2.25
    상
    2.22
    お客
    2.08
    とした
    1.94
    পক্ষে
    1.93
    ﺤ
    1.91
    ले
    1.90
    тура
    1.87
    ﻄ
    1.85
    รือ
    1.77
    Act Density 0.143%

    No Known Activations