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

    Neuronpedia

    INDEX
    Explanations

    numbers and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    то
    2.25
    𝒆
    1.85
    𝑭
    1.76
    СС
    1.66
    tr
    1.65
    ℝ
    1.64
    𝒚
    1.63
    atan
    1.62
    ится
    1.62
    ν
    1.60
    POSITIVE LOGITS
    ні
    2.27
    と感じ
    1.86
    ною
    1.84
    йд
    1.83
    గు
    1.62
    بان
    1.61
    ності
    1.61
    おり
    1.57
    ны
    1.56
     Sog
    1.55
    Act Density 0.299%

    No Known Activations