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

    Neuronpedia

    INDEX
    Explanations

    unicode character encoding handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    劑
    0.49
    thisStudent
    0.47
    weatherm
    0.45
    selfobj
    0.45
     arterioles
    0.45
    परेशन
    0.45
    ρού
    0.45
     fluidized
    0.43
     dė
    0.43
     checkIf
    0.43
    POSITIVE LOGITS
     Unicode
    1.98
    Unicode
    1.79
     unicode
    1.73
     UTF
    1.73
    unicode
    1.50
    UTF
    1.40
     utf
    1.39
    utf
    1.22
     encoding
    1.21
    Encoding
    1.16
    Act Density 0.073%

    No Known Activations