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

    Neuronpedia

    INDEX
    Explanations

    Inquiry Regarding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    3.41
    ان
    3.19
    an
    3.03
    ım
    2.98
    ীয়
    2.86
    ますが
    2.83
    ت
    2.70
    ます
    2.68
    anut
    2.64
    o
    2.62
    POSITIVE LOGITS
     proviene
    3.02
     chắn
    2.79
    ни
    2.77
     meiosis
    2.77
     ncol
    2.70
    те
    2.69
    robust
    2.63
    acoes
    2.62
    䒑
    2.59
    MACl
    2.59
    Act Density 0.013%

    No Known Activations