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

    Neuronpedia

    INDEX
    Explanations

    we followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    1.65
    ни
    1.51
    не
    1.25
    ا
    1.22
    ди
    1.17
    жа
    1.17
    й
    1.13
    ну
    1.11
    я
    1.09
    た
    1.09
    POSITIVE LOGITS
    केंसी
    0.98
    ção
    0.95
     fleste
    0.94
    vised
    0.93
    ंत्रिकी
    0.92
    chemical
    0.89
    ส์
    0.89
    enan
    0.89
    jenigen
    0.88
    phthal
    0.86
    Act Density 0.573%

    No Known Activations