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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms related to organizations and their definitions

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

    possessive or parenthetical identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.81
     صوتيه
    -0.76
     يتيمه
    -0.76
     Infórmanos
    -0.72
    UnusedPrivate
    -0.72
     ProtoMessage
    -0.69
     autorytatywna
    -0.69
     bezeichneter
    -0.68
     protoimpl
    -0.68
     ComVisible
    -0.67
    POSITIVE LOGITS
    ’
    0.60
     
    0.54
     is
    0.50
     have
    0.47
     provided
    0.47
     Grenz
    0.45
     provide
    0.45
    '
    0.45
    mathrm
    0.44
     made
    0.44
    Act Density 0.055%

    No Known Activations