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

    Neuronpedia

    INDEX
    Explanations

    portfolio, highways, prove, stripe, key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ś
    0.45
     daily
    0.43
     fir
    0.39
     twe
    0.39
     Fir
    0.39
     sian
    0.39
    吶
    0.38
     f
    0.38
     Daily
    0.37
     predicted
    0.37
    POSITIVE LOGITS
    Jenny
    0.44
    證
    0.43
    ಂಗ್ರೆ
    0.41
     అంబేద్కర్
    0.41
    ⋯
    0.39
     機
    0.39
    ূর্ন
    0.38
    িকে
    0.38
     النسبيه
    0.38
    隈
    0.38
    Act Density 0.000%

    No Known Activations