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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names related to individuals and organizations

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

    McKinley, degeneration, Tennant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    retudo
    -0.57
    emphasis
    -0.49
     esternos
    -0.48
     erity
    -0.46
    #
    -0.45
     agradec
    -0.44
     emphasis
    -0.44
     recuerda
    -0.43
     thanking
    -0.43
     høre
    -0.43
    POSITIVE LOGITS
     cervello
    0.46
    HasForeignKey
    0.45
    McKin
    0.45
     Edd
    0.43
    ghan
    0.43
    PhysRevD
    0.42
    ColumnInfo
    0.42
    IntoConstraints
    0.41
    ✨:
    0.41
    FunctionFlags
    0.40
    Act Density 0.129%

    No Known Activations