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

    Neuronpedia

    INDEX
    Explanations

    adding class attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Registry
    0.63
    Rating
    0.62
    。”
    0.61
    ReactDOM
    0.61
     على
    0.60
     نع
    0.60
    Override
    0.59
    Restriction
    0.59
    Stat
    0.59
     ระ
    0.59
    POSITIVE LOGITS
    s
    0.73
    чення
    0.64
    ные
    0.63
    lh
    0.60
    0.60
    ي
    0.59
     Gospel
    0.57
    y
    0.57
    )
    0.57
    lige
    0.57
    Act Density 0.002%

    No Known Activations