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

    Neuronpedia

    INDEX
    Explanations

    concepts related to statistical or mathematical expressions and parameters

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

    Numerical values found in tables

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.77
     Nadia
    -0.73
     McDonough
    -0.72
     Boles
    -0.69
     Regina
    -0.67
     Jessie
    -0.64
     Tet
    -0.62
     Shah
    -0.62
     Marek
    -0.61
    ESR
    -0.61
    POSITIVE LOGITS
     Joyce
    0.72
     '\\;'
    0.72
    #+#
    0.71
     Valverde
    0.69
     Langford
    0.68
    contentLoaded
    0.66
     Ambrose
    0.66
     garage
    0.66
     Wright
    0.66
     Blackburn
    0.65
    Act Density 0.936%

    No Known Activations