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

    Neuronpedia

    INDEX
    Explanations

    technical aspects related to integrated circuit design and functionality

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

    Follows conjunctions indicating contrast or example

    np_acts-logits-general · gemini-2.0-flash

    introduces specific examples or transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.84
     المعيارى
    -0.75
    Tembelea
    -0.70
    Cyfarwyddwr
    -0.69
     Taktlose
    -0.65
     nahilalakip
    -0.62
    WarningLevel
    -0.60
    Jîn
    -0.59
    DoubleQuotes
    -0.59
    :✨
    -0.59
    POSITIVE LOGITS
     poème
    0.43
     Ejército
    0.42
     Wert
    0.42
     rouleau
    0.40
     algodón
    0.40
     Economía
    0.40
    őben
    0.39
     vêtement
    0.39
     fleuve
    0.39
     río
    0.39
    Act Density 1.559%

    No Known Activations