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

    Neuronpedia

    INDEX
    Explanations

    concepts related to confidence and self-perception in communication

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

    quantifier/connector (e.g., first, between, approximately, per, multiple)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utilisons
    -0.40
     GenerationType
    -0.39
     card
    -0.31
    ExtendWith
    -0.31
    ness
    -0.29
    IntoConstraints
    -0.29
     casal
    -0.29
     bunga
    -0.28
     altogether
    -0.27
     young
    -0.27
    POSITIVE LOGITS
    Portail
    0.62
     kasarigan
    0.62
     الرياضيه
    0.60
    Portale
    0.59
    发表于
    0.56
    MENAFN
    0.55
     oprot
    0.53
    Portály
    0.53
    RTLE
    0.52
    WebElementEntity
    0.50
    Act Density 0.161%

    No Known Activations