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

    Neuronpedia

    INDEX
    Explanations

    data identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     number
    0.51
     সংখ্যা
    0.51
     year
    0.45
     numbers
    0.43
     αριθ
    0.42
     run
    0.41
     dat
    0.40
     ten
    0.40
     computed
    0.40
     Number
    0.39
    POSITIVE LOGITS
    نا
    0.43
    ⦕
    0.41
    ⦖
    0.41
    गौर
    0.40
    ১
    0.40
     ensimmä
    0.40
    🫶
    0.40
     اولین
    0.39
     terken
    0.39
    முதல்
    0.39
    Act Density 0.026%

    No Known Activations