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

    Neuronpedia

    INDEX
    Explanations

    references to user interface design concepts and alerts in coding contexts

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

    user input after turn start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.42
    Ӕ
    -0.42
     vœux
    -0.40
     fallu
    -0.40
     escol
    -0.38
     comprends
    -0.37
     disponíveis
    -0.36
    xfc
    -0.34
     halbe
    -0.34
     zwarte
    -0.33
    POSITIVE LOGITS
     storyboard
    0.90
    providedIn
    0.63
    Tembelea
    0.62
     lenker
    0.61
    MemoryWarning
    0.58
     surla
    0.56
    UVWXYZ
    0.56
     Undeclared
    0.56
    Hentet
    0.55
    Parcelize
    0.54
    Act Density 0.001%

    No Known Activations