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

    Neuronpedia

    INDEX
    Explanations

    list item numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    im
    0.59
    Петер
    0.58
    aud
    0.58
    minded
    0.57
    paced
    0.56
    तार
    0.56
    azote
    0.56
    oll
    0.54
    programm
    0.54
    ias
    0.54
    POSITIVE LOGITS
    ️⃣
    0.87
     Hành
    0.78
    ⃣
    0.77
     Myself
    0.73
    ️
    0.73
    .)..
    0.72
     On
    0.72
     Для
    0.72
     વૈ
    0.71
     從
    0.71
    Act Density 0.599%

    No Known Activations