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

    Neuronpedia

    INDEX
    Explanations

    abstract texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    हदी
    1.88
    धन
    1.81
    インチ
    1.79
    Chang
    1.79
    ഭവ
    1.79
    меч
    1.76
    সাল
    1.75
    naya
    1.74
    ढ़ाई
    1.73
    iemi
    1.72
    POSITIVE LOGITS
    DebugSymbols
    1.62
    romptu
    1.51
    ฟ้า
    1.45
    ᾽
    1.36
    ágina
    1.33
    áže
    1.33
    %>%
    1.31
     un
    1.30
    ڑے
    1.29
    냇
    1.27
    Act Density 0.036%

    No Known Activations