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

    Neuronpedia

    INDEX
    Explanations

    onion in lists of ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    0.90
    ۰
    0.72
    க்
    0.70
    يًا
    0.70
    ။
    0.70
    you
    0.68
    ي
    0.65
    ،
    0.65
    iiv
    0.65
    %。
    0.64
    POSITIVE LOGITS
    g
    0.86
    ’
    0.84
     Pierws
    0.79
    l
    0.79
     Erweiter
    0.78
    liceerd
    0.74
    t
    0.70
     onion
    0.70
     Matth
    0.69
     Feuerwehr
    0.69
    Act Density 0.002%

    No Known Activations