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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles in historical contexts

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

    dates in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.78
     فريبيس
    -0.64
     lyre
    -0.52
    IsPostBack
    -0.49
    лтемелер
    -0.46
    SceneManagement
    -0.46
     poveznice
    -0.46
    قایناق‌لار
    -0.44
     Rabat
    -0.44
    Bakgrunnsstoff
    -0.44
    POSITIVE LOGITS
    RegressionTest
    0.50
     upacara
    0.41
    tivitas
    0.40
     estratégia
    0.40
    arschijnlijk
    0.39
     Auft
    0.39
     údaj
    0.39
     Strategie
    0.39
     nocturno
    0.39
    //
    0.38
    Act Density 0.064%

    No Known Activations