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

    Neuronpedia

    INDEX
    Explanations

    content-type headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     대로
    0.44
     ऐसी
    0.41
     férfi
    0.40
    涅
    0.40
     பூ
    0.40
     culminates
    0.39
     sais
    0.39
    瑢
    0.39
    顼
    0.39
    ந்து
    0.38
    POSITIVE LOGITS
    xml
    0.61
    binary
    0.54
     binary
    0.53
     xml
    0.50
     XML
    0.49
     Binary
    0.47
    executable
    0.46
    XML
    0.45
    serialized
    0.44
    Xml
    0.43
    Act Density 0.003%

    No Known Activations