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

    Neuronpedia

    INDEX
    Explanations

    dialogue and conversation indicators in text

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

    Attribution of quotes to people

    np_acts-logits-general · gemini-2.0-flash

    reported speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.67
    étranger
    -0.61
     seuls
    -0.56
    Collegamenti
    -0.56
    urrent
    -0.56
     виправивши
    -0.55
    Vorlage
    -0.54
    leun
    -0.53
     déclen
    -0.52
    vri
    -0.50
    POSITIVE LOGITS
    HostException
    0.59
     GenerationType
    0.58
     praise
    0.56
    UrlResolution
    0.54
     reporters
    0.54
     praising
    0.53
    HttpFoundation
    0.53
    ########.
    0.53
    DeleteMapping
    0.52
    HandlerContext
    0.52
    Act Density 0.101%

    No Known Activations