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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics

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

    Numbers followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -1.09
    ISupport
    -1.07
     EconPapers
    -1.02
     ویکی‌پدیای
    -0.95
    AndEndTag
    -0.94
    writeFieldEnd
    -0.91
     оригіналу
    -0.91
    GraphicsUnit
    -0.90
    DeleteBehavior
    -0.90
    rungsseite
    -0.89
    POSITIVE LOGITS
    _
    0.47
    2
    0.45
    1
    0.44
    3
    0.44
    8
    0.42
    7
    0.42
    6
    0.41
    4
    0.41
     image
    0.41
     
    0.40
    Act Density 0.065%

    No Known Activations