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

    Neuronpedia

    INDEX
    Explanations

    conversational prompts and expressions indicating comprehension or engagement

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

    conversational interjections and confirmations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.40
    disposing
    -0.38
     occaf
    -0.37
    Оценка
    -0.34
     ratón
    -0.34
     poffe
    -0.33
     OnTrigger
    -0.33
    daction
    -0.33
     Grüsse
    -0.33
     filtro
    -0.32
    POSITIVE LOGITS
    HtmlAttribute
    0.68
     kasarigan
    0.68
    ImageContext
    0.57
    XmlType
    0.56
    ActionCreators
    0.54
     <<<<<<<<<<<<<<
    0.52
    Personendaten
    0.52
    ftagPool
    0.47
    awtextra
    0.47
    WriteTagHelper
    0.47
    Act Density 0.175%

    No Known Activations