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

    Neuronpedia

    INDEX
    Explanations

    It's like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    लेटर
    0.73
    และการ
    0.69
    రీలు
    0.69
    နှုန်း
    0.69
    ه‌ها
    0.67
    waitKey
    0.67
    طلح
    0.66
     confronted
    0.66
     subscripts
    0.65
     confiscated
    0.65
    POSITIVE LOGITS
     ofthe
    1.87
     of
    1.82
     off
    1.71
     pf
    1.60
     ऑफ
    1.55
     của
    1.50
    ของ
    1.47
    of
    1.47
     ऑफ़
    1.46
     fo
    1.46
    Act Density 0.000%

    No Known Activations