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

    Neuronpedia

    INDEX
    Explanations

    intensifiers or adjectives indicating a high degree of something

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

    very + adjective/adverb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.43
    figcaption
    -0.42
    StoryboardSegue
    -0.41
    Искәрмәләр
    -0.40
    InjectAttribute
    -0.40
    ContentLoaded
    -0.39
    OrNil
    -0.39
     Balfour
    -0.38
    WriteLiteral
    -0.37
    erda
    -0.37
    POSITIVE LOGITS
    Very
    0.61
     very
    0.61
     deose
    0.58
    Çok
    0.56
     очень
    0.56
    räck
    0.55
     Очень
    0.55
     дуже
    0.55
    Bardzo
    0.54
     Bardzo
    0.54
    Act Density 0.039%

    No Known Activations