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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or contexts indicating actions that were not completed or determined

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

    programming test infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">//
    -0.42
    झ
    -0.38
    jure
    -0.38
    Билгалдахарш
    -0.37
    カンド
    -0.37
     comuniques
    -0.36
    lə
    -0.36
     simplifié
    -0.36
    som
    -0.35
     die
    -0.34
    POSITIVE LOGITS
    libft
    0.52
     crossorigin
    0.48
    UrlResolution
    0.47
    TestingModule
    0.47
    AccessorTable
    0.45
    tagHelperRunner
    0.45
    ronpa
    0.45
    SharedCtor
    0.44
     كومونز
    0.43
    GraphicsUnit
    0.43
    Act Density 0.116%

    No Known Activations