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

    Neuronpedia

    INDEX
    Explanations

    tokens and symbols that denote specific actions or items, particularly in relation to games and health metrics

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

    mental component

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.65
     useAppContext
    -0.57
    contentLoaded
    -0.54
    NameInMap
    -0.51
    verwijspagina
    -0.48
    -0.47
     flesta
    -0.46
    UnitTesting
    -0.46
     wesentlichen
    -0.46
    rungsseite
    -0.46
    POSITIVE LOGITS
     Bof
    0.45
     UIKit
    0.43
    Pin
    0.42
    China
    0.41
    Pon
    0.41
    Roman
    0.41
    Polar
    0.41
    astify
    0.40
    Chu
    0.40
     felicità
    0.40
    Act Density 0.038%

    No Known Activations