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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating assertions or declarations

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

    "i say" or "call"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chofe
    -0.39
     pleaſure
    -0.38
     fubject
    -0.37
     perdón
    -0.35
     sánchez
    -0.34
    CppMethod
    -0.33
     ifrån
    -0.33
     dépens
    -0.33
     détru
    -0.32
     pleaf
    -0.32
    POSITIVE LOGITS
     ModelExpression
    0.62
    出版年
    0.59
     surla
    0.59
    UrlResolution
    0.59
    Datuak
    0.55
    addGap
    0.55
    TemporalType
    0.53
    MigrationBuilder
    0.52
     BorderRadius
    0.51
    RequestMethod
    0.51
    Act Density 0.088%

    No Known Activations