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

    Neuronpedia

    INDEX
    Explanations

    elements or structures resembling numerical systems or data formats, particularly those categorized by symbols and alphanumeric sequences

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

    Hexadecimal and decimal numbers

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -1.05
     <<<<<<<<<<<<<<
    -0.99
    ագրություններ
    -0.90
    -------------</
    -0.89
     estekak
    -0.89
    Билгалдахарш
    -0.86
    ImageContext
    -0.85
     Numerade
    -0.85
    Datuak
    -0.84
     @"/
    -0.84
    POSITIVE LOGITS
    1
    0.66
    2
    0.65
    3
    0.63
    4
    0.62
    7
    0.60
    5
    0.60
    8
    0.57
    9
    0.56
    6
    0.56
    0
    0.54
    Act Density 0.982%

    No Known Activations