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

    Neuronpedia

    INDEX
    Explanations

    references to sensitive information stored as environment variables

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

    credentials available or needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CLAIM
    -0.36
    SIZES
    -0.35
    lgari
    -0.35
     cumplido
    -0.35
    ittle
    -0.34
     voulu
    -0.33
     apporté
    -0.33
     claim
    -0.33
    ETERS
    -0.32
    atici
    -0.32
    POSITIVE LOGITS
    aarrggbb
    0.61
     незавершена
    0.59
    dotenv
    0.57
    oa̍t
    0.57
    UrlResolution
    0.57
     snippetHide
    0.57
     дописавши
    0.56
    ArgsConstructor
    0.56
    PreExecute
    0.54
     ModelExpression
    0.54
    Act Density 0.054%

    No Known Activations