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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and commands indicating collaboration or interaction

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

    initiating action or discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Дереккөздер
    -0.53
    WebElementEntity
    -0.52
     Administrativna
    -0.52
     AppCompatTheme
    -0.48
    ransition
    -0.48
    complexContent
    -0.47
     miniaturka
    -0.47
    -0.47
     lenker
    -0.47
    rungsseite
    -0.46
    POSITIVE LOGITS
     discussion
    0.52
     conversation
    0.45
    BagLayout
    0.45
     session
    0.42
     CONVERS
    0.42
     SESSION
    0.40
    discussion
    0.40
     tuss
    0.40
    versation
    0.40
     constexpr
    0.39
    Act Density 0.035%

    No Known Activations