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

    Neuronpedia

    INDEX
    Explanations

    contexts where manipulation and intelligence are highlighted in character actions

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

    Follows adverbs of manner (quickly)

    np_acts-logits-general · gemini-2.0-flash

    know everything and anything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MockBean
    -0.48
     autorytatywna
    -0.46
    Personendaten
    -0.42
    prüche
    -0.41
    JAKARTA
    -0.41
    Gordon
    -0.40
    پاسخ
    -0.39
    Unmount
    -0.39
     increasing
    -0.39
    bonne
    -0.39
    POSITIVE LOGITS
    siempre
    0.45
     vientre
    0.42
    HtmlAttribute
    0.42
    ้งาน
    0.42
     zawsze
    0.42
     siempre
    0.41
     altijd
    0.40
     perhatian
    0.39
    DoubleQuotes
    0.38
     AssemblyCompany
    0.38
    Act Density 0.291%

    No Known Activations