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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and ideas related to various products or concepts, particularly focusing on the effects and outcomes associated with them

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

    racial discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ktop
    -0.65
    migrationBuilder
    -0.64
    Diweddarwch
    -0.61
    ThroughAttribute
    -0.57
    ]")]
    -0.56
    esgue
    -0.54
    agonal
    -0.53
     ſeine
    -0.52
    \{\\
    -0.52
     surla
    -0.52
    POSITIVE LOGITS
     everywhere
    0.33
    @[+][
    0.32
     EVERYTHING
    0.32
     sprinkled
    0.32
     web
    0.32
     gober
    0.30
    正面
    0.30
     Haushalt
    0.29
     überall
    0.29
     armado
    0.29
    Act Density 0.075%

    No Known Activations