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

    Neuronpedia

    INDEX
    Explanations

    included options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     شويه
    0.50
     trochu
    0.50
    ちょっと
    0.49
     কিছুটা
    0.45
     lately
    0.45
     lidt
    0.44
     nieco
    0.44
     sedikit
    0.43
     Lately
    0.43
     somewhat
    0.43
    POSITIVE LOGITS
     глав
    0.39
     τρί
    0.38
    ጨማሪ
    0.38
    的主要
    0.37
     الرئيسية
    0.37
    cella
    0.37
    ILI
    0.36
    lüssel
    0.36
     ممکن
    0.35
    সমূহ
    0.35
    Act Density 0.005%

    No Known Activations