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

    Neuronpedia

    INDEX
    Explanations

    . or - followed by word/number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ana
    0.32
     întreb
    0.30
     Grange
    0.29
    vano
    0.29
    oro
    0.28
     موضوع
    0.28
     astrolog
    0.28
     Cicero
    0.28
     লোকের
    0.28
     Chopin
    0.28
    POSITIVE LOGITS
    を使う
    0.33
    א
    0.33
    や
    0.33
    의
    0.32
    েরে
    0.32
    の
    0.32
    ն
    0.32
    ను
    0.31
    的
    0.31
    ಗೆ
    0.31
    Act Density 0.028%

    No Known Activations