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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions related to value functions in decision-making processes

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

    policy evaluation and learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NUMX
    -0.48
     pageable
    -0.41
    guém
    -0.41
     رخ
    -0.40
    NameInMap
    -0.40
     Morrissey
    -0.40
    PathVariable
    -0.39
    icksburg
    -0.39
    InitVars
    -0.38
     Papp
    -0.38
    POSITIVE LOGITS
    tagHelperRunner
    0.47
     MenuView
    0.42
     view
    0.40
    тату
    0.40
     anim
    0.40
    NameLabel
    0.39
     ContentValues
    0.38
    assassin
    0.37
    🎰
    0.37
     légale
    0.36
    Act Density 0.032%

    No Known Activations