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

    Neuronpedia

    INDEX
    Explanations

    classification codes or errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﾜ
    0.41
    𒀸
    0.40
    ዊ
    0.39
    ഭ്യാ
    0.39
    腊
    0.38
    臘
    0.38
    اك
    0.38
     interd
    0.37
    plers
    0.36
    チャ
    0.36
    POSITIVE LOGITS
     sic
    0.55
     SIC
    0.43
     Sic
    0.42
    urezza
    0.40
    fuzzy
    0.39
     Fiat
    0.38
     Identified
    0.38
     tiến
    0.37
    Sic
    0.37
     sek
    0.36
    Act Density 0.001%

    No Known Activations