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

    Neuronpedia

    INDEX
    Explanations

    coding and technical terms related to functionality and assessment

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

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.80
     Taktlose
    -0.73
    principalTable
    -0.70
    setVerticalGroup
    -0.69
    SharedDtor
    -0.68
    ьаж
    -0.68
    OGND
    -0.67
    oredCriteria
    -0.66
     Paglinawan
    -0.66
     المعيارى
    -0.66
    POSITIVE LOGITS
    帖最后由
    0.39
    ᅠ
    0.37
     pantolon
    0.35
     Metzger
    0.30
    сь
    0.29
     doors
    0.29
     Reflect
    0.28
    なぜか
    0.28
    imp
    0.28
    ito
    0.28
    Act Density 0.024%

    No Known Activations