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

    Neuronpedia

    INDEX
    Explanations

    obscenity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    าลัย
    0.77
    诸
    0.76
    icuous
    0.75
     quid
    0.71
    straction
    0.71
    埌
    0.68
     ChromeDriver
    0.66
     undeni
    0.66
    ர்ந்து
    0.65
    াড়
    0.65
    POSITIVE LOGITS
    enian
    0.83
    nan
    0.79
     বর্ধ
    0.78
    dan
    0.78
    enan
    0.77
    uvat
    0.75
    en
    0.75
    an
    0.74
    lad
    0.73
    mehr
    0.73
    Act Density 0.001%

    No Known Activations