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

    Neuronpedia

    INDEX
    Explanations

    elements of code related to functions and variables

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

    GraphQL query or subscription syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.98
     ModelExpression
    -0.75
    ValueStyle
    -0.75
    +#+#
    -0.72
     समीक्षाओं
    -0.71
     queſta
    -0.69
    <unused43>
    -0.68
    <unused28>
    -0.68
    <unused8>
    -0.68
    [@BOS@]
    -0.68
    POSITIVE LOGITS
     I
    0.42
     ar
    0.35
     Gro
    0.35
     …
    0.35
     gro
    0.34
    湯
    0.34
     Lau
    0.34
    StatusOK
    0.34
     rest
    0.33
     DbSet
    0.33
    Act Density 0.011%

    No Known Activations