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

    Neuronpedia

    INDEX
    Explanations

    concepts related to giving, power, and doctrines

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

    doctrine of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asuntos
    -0.37
    ">//
    -0.35
     domanda
    -0.35
    attenzione
    -0.35
     uſed
    -0.34
     goederen
    -0.34
     Atau
    -0.33
     jongen
    -0.33
     exécu
    -0.33
     ennemi
    -0.32
    POSITIVE LOGITS
    extAlignment
    0.79
    AxisAlignment
    0.65
     мәкал
    0.65
    QMetaType
    0.63
     arbitrage
    0.62
     brainstorming
    0.59
     laziness
    0.59
    aimeJ
    0.58
     stealth
    0.57
     sabotage
    0.57
    Act Density 0.030%

    No Known Activations