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

    Neuronpedia

    INDEX
    Explanations

    formal decision-making processes and associated actions

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

    decisions and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cheesy
    -0.44
    batore
    -0.39
    RegistryLite
    -0.38
     newBuilder
    -0.38
     Gl
    -0.38
     night
    -0.38
     rusty
    -0.37
    hyrchwyd
    -0.37
     Bren
    -0.37
     misses
    -0.37
    POSITIVE LOGITS
     CURIAM
    0.53
    exitRule
    0.47
    appé
    0.46
    Hozzáférés
    0.44
    EDEFAULT
    0.42
    VersionUID
    0.42
    wój
    0.41
    keyColumn
    0.41
    DockStyle
    0.40
     propOrder
    0.40
    Act Density 0.025%

    No Known Activations