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

    Neuronpedia

    INDEX
    Explanations

    prefixes for specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বৎসরের
    0.30
    度和
    0.28
    𒅌
    0.28
     iedereen
    0.28
    银行
    0.27
    性和
    0.26
    italizationType
    0.26
    ="";
    0.26
     Housewives
    0.25
     अनी
    0.25
    POSITIVE LOGITS
     relic
    0.28
    ها
    0.27
     taint
    0.27
     mAbs
    0.26
    ћ
    0.26
    opters
    0.26
     foci
    0.26
    վ
    0.26
     tad
    0.25
    ہیں
    0.25
    Act Density 0.148%

    No Known Activations