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

    Neuronpedia

    INDEX
    Explanations

    titles followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    サーバ
    0.31
    Ꮽ
    0.30
    ੈ
    0.30
    -
    0.30
    🚉
    0.30
    От
    0.29
    sthe
    0.29
     natively
    0.28
    ЕНИ
    0.28
     Ecusson
    0.28
    POSITIVE LOGITS
    Y
    0.38
     Beverage
    0.35
     nicht
    0.34
     တစ်
    0.34
     një
    0.33
     não
    0.33
    A
    0.32
    5
    0.32
     Illuminate
    0.32
     nhau
    0.31
    Act Density 0.019%

    No Known Activations