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

    Neuronpedia

    INDEX
    Explanations

    in a way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ie
    0.75
     for
    0.73
     компью
    0.73
     cookbooks
    0.73
    od
    0.72
     фрук
    0.72
     mollus
    0.72
    outines
    0.71
     vodka
    0.68
     vacuoles
    0.68
    POSITIVE LOGITS
     ambayo
    0.80
    ي
    0.78
    ,
    0.77
    ซึ่ง
    0.76
    (
    0.71
    ம்
    0.70
    ส
    0.69
    .
    0.68
    ות
    0.67
    p
    0.67
    Act Density 0.049%

    No Known Activations