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

    Neuronpedia

    INDEX
    Explanations

    leave on, left out, left shoulder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    其他
    2.02
    ak
    1.98
     variés
    1.94
     الموافق
    1.92
    िया
    1.85
    ى
    1.80
     américains
    1.78
    ें
    1.73
     economici
    1.73
    iezan
    1.71
    POSITIVE LOGITS
    م
    2.72
    ING
    2.38
    σιμοποι
    2.33
    taker
    2.31
    る
    2.27
    ر
    2.20
    র
    2.16
     помогут
    2.11
    тта
    2.08
    ר
    2.06
    Act Density 0.502%

    No Known Activations