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

    Neuronpedia

    INDEX
    Explanations

    placeholder texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙉
    3.13
     Escola
    3.05
    в
    3.03
     impulse
    2.91
    ,}
    2.88
    গত
    2.84
     textField
    2.84
    ઝ
    2.81
    Chọn
    2.80
     pār
    2.73
    POSITIVE LOGITS
    holders
    3.71
    랫폼
    3.04
    ें
    2.98
     окон
    2.95
    ו
    2.81
    ながら
    2.75
    ها
    2.72
    ю
    2.65
    ع
    2.64
    em
    2.63
    Act Density 0.028%

    No Known Activations