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

    Neuronpedia

    INDEX
    Explanations

    marketing slogans, dates, names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    癥
    0.41
    輌
    0.40
     [(
    0.37
     konus
    0.37
    こな
    0.37
     sam
    0.36
    arently
    0.36
    ave
    0.36
    ämä
    0.35
     subset
    0.35
    POSITIVE LOGITS
    法语
    0.45
     Roxy
    0.44
    Roxy
    0.44
    يانة
    0.43
    ைகள்
    0.42
    诲
    0.40
    ไซ
    0.39
    ʒ
    0.39
     جاتے
    0.39
     Nicki
    0.38
    Act Density 0.000%

    No Known Activations