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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in programming or coding contexts

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

    format;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.77
     فريبيس
    -0.65
    interopRequire
    -0.63
     nahilalakip
    -0.59
    __":
    -0.59
    }{*}{}
    -0.57
     Theſe
    -0.52
    -0.52
     Houſe
    -0.52
     zwiſchen
    -0.50
    POSITIVE LOGITS
    Soorten
    0.34
    bello
    0.34
     ří
    0.32
    true
    0.32
    .*;
    0.32
    aufs
    0.32
    CodedInputStream
    0.31
    domésticos
    0.30
    heids
    0.30
     Shapiro
    0.30
    Act Density 0.363%

    No Known Activations