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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ventaja
    0.48
     híbr
    0.47
    Wasser
    0.47
     superfici
    0.46
    वेदना
    0.46
    🔁
    0.46
     rửa
    0.45
     }-\
    0.45
     Craigslist
    0.45
    ႁ
    0.45
    POSITIVE LOGITS
     */
    0.47
    //
    0.41
     *
    0.41
    */
    0.39
    าย
    0.37
     जुलाई
    0.36
    下面的
    0.35
    env
    0.35
    وفي
    0.34
    esini
    0.34
    Act Density 0.116%

    No Known Activations