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

    Neuronpedia

    INDEX
    Explanations

    compiler directives and warnings in coding contexts

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

    disabling or disabling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    beitet
    -0.46
    ᅠ
    -0.43
     Италијани
    -0.43
     peines
    -0.42
    NewUrlParser
    -0.42
    ConstraintMaker
    -0.41
     disambiguazione
    -0.41
    Indented
    -0.40
     okuyayım
    -0.40
     suyo
    -0.40
    POSITIVE LOGITS
     disable
    1.80
     Disable
    1.32
     disables
    1.23
     disabling
    1.20
     disabled
    1.13
     DISABLE
    0.99
    Disable
    0.99
    disable
    0.91
     Disabled
    0.85
    disabled
    0.75
    Act Density 0.002%

    No Known Activations