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

    Neuronpedia

    INDEX
    Explanations

    lists or specific punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Portion
    0.47
     Margin
    0.46
    மணி
    0.45
     Brim
    0.44
     Textile
    0.44
     Daytime
    0.44
    น
    0.43
    鬘
    0.43
     Faith
    0.43
     Tuscany
    0.42
    POSITIVE LOGITS
     servidor
    0.50
    𝟬
    0.50
    Slow
    0.47
     comida
    0.44
     gevo
    0.43
    ADO
    0.42
    PAC
    0.42
     dod
    0.42
     publicados
    0.42
     ഏത
    0.41
    Act Density 0.000%

    No Known Activations