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

    Neuronpedia

    INDEX
    Explanations

    non-english phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contractions
    0.48
    разу
    0.45
    NDA
    0.44
     FTA
    0.44
    setTime
    0.43
     Programa
    0.42
     contraction
    0.40
     graham
    0.40
     contractual
    0.39
    Program
    0.39
    POSITIVE LOGITS
     월
    0.50
     구입
    0.47
     ਕਿਸ
    0.46
     పేరు
    0.45
    בים
    0.44
     فروش
    0.44
     बर्बाद
    0.44
     toyota
    0.44
    noof
    0.44
     무료
    0.44
    Act Density 0.006%

    No Known Activations