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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and numerical representations within the text

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

    Numbers in parentheses followed by brackets

    np_acts-logits-general · gemini-2.0-flash

    numbers and ordinal numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ivelany
    -0.59
    4
    -0.57
     civiles
    -0.55
     gynhyrchwyd
    -0.53
     المعيارى
    -0.53
     IV
    -0.53
     fourth
    -0.52
     keempat
    -0.50
     Fourth
    -0.48
    GEBURTSDATUM
    -0.48
    POSITIVE LOGITS
     Tenth
    0.66
    HostException
    0.62
     Twelve
    0.60
     twelfth
    0.59
     Twelfth
    0.57
     twelve
    0.56
     AssemblyCulture
    0.54
     tenth
    0.54
     ten
    0.51
    AutoField
    0.51
    Act Density 0.574%

    No Known Activations