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

    Neuronpedia

    INDEX
    Explanations

    types and preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.80
    та
    0.71
     една
    0.66
     б
    0.66
     caoutch
    0.63
     едно
    0.63
     У
    0.61
     లు
    0.61
     emergency
    0.61
     bronze
    0.61
    POSITIVE LOGITS
    вый
    0.86
     intentos
    0.83
     awfully
    0.80
    г
    0.80
    ,)
    0.78
    蛋白
    0.76
    スクリーン
    0.76
     Kräfte
    0.75
     نہيں
    0.74
    sch
    0.73
    Act Density 0.002%

    No Known Activations