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

    Neuronpedia

    INDEX
    Explanations

    programming and markup language syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, XML, or markup syntax

    np_acts-logits-general · gemini-2.0-flash

    code structures and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lisse
    -0.48
     though
    -0.46
    ždý
    -0.45
    By
    -0.43
    īgs
    -0.42
    tagext
    -0.42
     helyez
    -0.41
    bbene
    -0.40
    彡
    -0.40
    AssignableFrom
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.95
    uxxxx
    0.82
    Personensuche
    0.80
    تقاوى
    0.80
     Signalez
    0.78
    aarrggbb
    0.78
    Autoritní
    0.77
     Савезне
    0.77
    GEBURTSDATUM
    0.77
    "]).
    0.77
    Act Density 0.503%

    No Known Activations