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

    Neuronpedia

    INDEX
    Explanations

    instances of unique document formatting or database identifiers

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

    Capital letters

    np_acts-logits-general · gemini-2.0-flash

    Q; Dex; Cardiac; Various; Large; Cole; M; The; Der; Be; Ke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     >=",
    -0.94
     AssemblyCulture
    -0.90
     StatelessWidget
    -0.86
    ########.
    -0.85
    ReusableCell
    -0.81
    ResumeLayout
    -0.81
    脚注の使い方
    -0.81
     noDo
    -0.79
    MigrationBuilder
    -0.78
    StructEnd
    -0.77
    POSITIVE LOGITS
     A
    0.85
     J
    0.83
     E
    0.80
     R
    0.76
     C
    0.74
     M
    0.71
     L
    0.67
     S
    0.66
     P
    0.65
     F
    0.65
    Act Density 0.192%

    No Known Activations