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

    Neuronpedia

    INDEX
    Explanations

    end of code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flats
    0.65
     Altman
    0.65
     鳥
    0.63
     Zweifel
    0.62
    Ω
    0.62
    bull
    0.62
    sil
    0.61
    alternate
    0.61
     lawful
    0.60
     Show
    0.60
    POSITIVE LOGITS
     خود
    0.70
     capucha
    0.68
    愪
    0.62
     bagno
    0.62
     ሁሉ
    0.61
    ಂಧ
    0.61
    ئي
    0.61
     ಹೇಳ
    0.61
    मिका
    0.61
     /**@
    0.60
    Act Density 0.023%

    No Known Activations