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

    Neuronpedia

    INDEX
    Explanations

    key terms related to fundamental concepts and categories

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

    exact configuration

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that initiate or frame important phrases or technical constructs (phrase-onset markers like articles, discourse connectors, acronyms/math notation).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     RB
    -0.35
    verifyException
    -0.33
    #
    -0.31
    ステ
    -0.31
    アド
    -0.31
    Mit
    -0.29
    
    -0.29
     inten
    -0.29
     MB
    -0.29
    تع
    -0.29
    POSITIVE LOGITS
    BeginInit
    0.75
    MessageOf
    0.71
    EndInit
    0.64
     transfieras
    0.64
    migrationBuilder
    0.61
     wikipagina
    0.60
    expandindo
    0.59
    RenderAtEndOf
    0.59
    RemoveField
    0.57
     sanitarias
    0.57
    Act Density 0.135%

    No Known Activations