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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific parentheses or brackets in text

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

    lists of numbered items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     же
    -0.42
     OK
    -0.41
    OK
    -0.41
    .
    -0.40
     din
    -0.40
     of
    -0.39
    HP
    -0.39
     respectively
    -0.38
     Bohn
    -0.38
     Cap
    -0.36
    POSITIVE LOGITS
    tagHelperRunner
    0.85
     للاسماء
    0.74
    VersionUID
    0.74
    verwijspagina
    0.73
    StoryboardSegue
    0.72
    0.72
    stylers
    0.66
     AssemblyCulture
    0.66
    LookAnd
    0.65
    addCriterion
    0.64
    Act Density 0.009%

    No Known Activations