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

    Neuronpedia

    INDEX
    Explanations

    author initials and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ισ
    0.37
    ٤
    0.35
    である
    0.33
    ファイル
    0.33
     are
    0.33
    𝟏
    0.32
     AI
    0.32
     biomarkers
    0.31
     katk
    0.31
     JSON
    0.31
    POSITIVE LOGITS
     schützen
    0.35
     oryg
    0.34
    ﹌
    0.33
     ingat
    0.33
    lick
    0.32
    过的
    0.32
    ně
    0.31
     এবং
    0.30
    initConfig
    0.30
     supposing
    0.30
    Act Density 0.002%

    No Known Activations