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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a request or outcome

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

    out a / of / the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     efficaces
    -0.44
     inesper
    -0.43
     inesperado
    -0.42
     ketika
    -0.42
     líquida
    -0.41
     tristesse
    -0.41
     vacía
    -0.40
     vandaag
    -0.39
     decisión
    -0.39
     giusto
    -0.39
    POSITIVE LOGITS
    NameInMap
    0.75
    Personendaten
    0.60
    rungsseite
    0.55
     Scrap
    0.52
    XmlAccessorType
    0.52
     sex
    0.52
    WithIOException
    0.50
    MENAFN
    0.50
    setVerticalGroup
    0.49
     scrap
    0.48
    Act Density 0.005%

    No Known Activations