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

    Neuronpedia

    INDEX
    Explanations

    references to psychological traits and physical posture

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

    character and appetite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.71
    parsedMessage
    -0.68
    querySelectorAll
    -0.65
     صوتيه
    -0.62
     indisponible
    -0.61
    NewLabel
    -0.60
     nonUne
    -0.59
     informée
    -0.59
     $_(
    -0.59
    ghijklmnop
    -0.58
    POSITIVE LOGITS
     morale
    0.46
     integridad
    0.40
     Verfassung
    0.39
     reputación
    0.37
     creencias
    0.36
     reputation
    0.35
    lineHeight
    0.34
     mejorado
    0.34
     actitudes
    0.34
     integrity
    0.33
    Act Density 0.046%

    No Known Activations