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

    Neuronpedia

    INDEX
    Explanations

    keywords related to positive roles and qualities of individuals, especially within family and community contexts

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

    people roles and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HtmlAttribute
    -0.43
    ruik
    -0.38
    buttonShape
    -0.36
    protoc
    -0.34
    ReferenceEquals
    -0.34
    endmodule
    -0.33
    endregion
    -0.32
    ρίς
    -0.32
    的是
    -0.32
    省市镇
    -0.31
    POSITIVE LOGITS
    يميديا
    0.58
     enfans
    0.57
    rungsseite
    0.55
    +#+#
    0.54
    tvguidetime
    0.54
    <unused28>
    0.54
    <unused41>
    0.54
    <unused14>
    0.54
    <pad>
    0.54
    <unused3>
    0.54
    Act Density 0.039%

    No Known Activations