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

    Neuronpedia

    INDEX
    Explanations

    multi-language phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    constexpr
    2.74
    doing
    2.64
    "",
    2.52
    ্রিক
    2.46
    euler
    2.46
     reeling
    2.45
    லாமல்
    2.44
     sobbing
    2.37
     gsub
    2.36
    CGPoint
    2.34
    POSITIVE LOGITS
    ли
    3.26
    le
    2.98
     самому
    2.92
     absolument
    2.73
     वालों
    2.57
    м
    2.55
     וכ
    2.54
    á
    2.49
    なりません
    2.49
    ૦
    2.45
    Act Density 0.013%

    No Known Activations