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

    Neuronpedia

    INDEX
    Explanations

    parts of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ra
    0.62
    ี้
    0.56
    ارا
    0.54
    ਰ
    0.54
    什么
    0.53
    ↵↵
    0.50
    .
    0.49
    an
    0.48
    edere
    0.48
    ش
    0.46
    POSITIVE LOGITS
    ма
    0.83
    :
    0.78
    í
    0.69
    ח
    0.68
    ко
    0.67
    с
    0.67
    у
    0.66
    ：
    0.66
    é
    0.64
    ки
    0.63
    Act Density 2.858%

    No Known Activations