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

    Neuronpedia

    INDEX
    Explanations

    code and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.92
     estadounidense
    0.89
    стый
    0.88
     svou
    0.86
     오전
    0.84
    на
    0.82
     Многие
    0.82
    r
    0.80
     싶
    0.79
    ﺔ
    0.79
    POSITIVE LOGITS
     înce
    0.82
     పెరుగు
    0.78
     Nucleaires
    0.77
     Wisdom
    0.73
    𝘄
    0.71
    mss
    0.71
    𝗴
    0.70
    ophage
    0.69
    omeric
    0.68
     însă
    0.68
    Act Density 0.000%

    No Known Activations