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

    Neuronpedia

    INDEX
    Explanations

    references to being the first or an original instance of something

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

    first of its kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksika
    -0.43
     extranjera
    -0.35
     disegni
    -0.35
    OrEmpty
    -0.35
     Stew
    -0.34
     Wash
    -0.34
     confronti
    -0.34
     thermique
    -0.33
     asamblea
    -0.33
     fidèles
    -0.33
    POSITIVE LOGITS
    OGND
    0.73
    verwijspagina
    0.68
    rungsseite
    0.66
     NSCoder
    0.65
    WebElementEntity
    0.59
     kaarangay
    0.58
    ftagPool
    0.58
     nakalista
    0.56
    offsetof
    0.56
    ✨:
    0.56
    Act Density 0.029%

    No Known Activations