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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and numerical values in the text

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

    Numbers followed by brackets

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by ] or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.61
     Réponses
    -0.56
    LLocation
    -0.51
    ۰۰
    -0.50
    ObjectMeta
    -0.50
     EconPapers
    -0.50
    WaitGroup
    -0.50
    روید
    -0.49
     review
    -0.49
    __((
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.64
     disponibilités
    0.52
     Exceptions
    0.52
    nezeu
    0.51
     виправивши
    0.50
     вікі
    0.50
    ۱
    0.50
     rezer
    0.50
     contextLoads
    0.49
    Capac
    0.49
    Act Density 0.725%

    No Known Activations