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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data and variables

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

    Tokens within image filenames or tables

    np_acts-logits-general · gemini-2.0-flash

    digits and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adpleegd
    -0.71
     isInitialized
    -0.71
     CreateTagHelper
    -0.63
    URLException
    -0.63
     typelib
    -0.62
    setVerticalGroup
    -0.62
    prefixer
    -0.59
     unknownFields
    -0.59
     propOrder
    -0.55
    ”,
    -0.55
    POSITIVE LOGITS
    _
    1.01
    \_
    0.97
    \%
    0.77
    __
    0.74
    _-_
    0.70
     \%
    0.68
     Untitled
    0.68
    _\
    0.67
    ._
    0.66
     \_
    0.64
    Act Density 0.351%

    No Known Activations