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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms related to programming and data processing

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

    N followed by pgsql or user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.68
     himſelf
    -0.66
     canst
    -0.65
    ſelf
    -0.64
    windowFixed
    -0.63
     myſelf
    -0.60
    AntiForgeryToken
    -0.59
    DoubleQuotes
    -0.59
     juſ
    -0.58
     itſelf
    -0.58
    POSITIVE LOGITS
     N
    0.63
     E
    0.51
     Gra
    0.51
     K
    0.50
     F
    0.50
     J
    0.49
     W
    0.48
     H
    0.47
     L
    0.47
     Fast
    0.47
    Act Density 0.019%

    No Known Activations