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

    Neuronpedia

    INDEX
    Explanations

    web addresses and URLs

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

    Tokens before or after a forward slash

    np_acts-logits-general · gemini-2.0-flash

    URLs, file paths, and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auffi
    -0.69
    Показать
    -0.67
     Tenggara
    -0.66
     deſt
    -0.66
     Likewise
    -0.64
     purpoſe
    -0.63
    WireFormatLite
    -0.62
     raiſ
    -0.61
    SharedDtor
    -0.61
     faſt
    -0.61
    POSITIVE LOGITS
    featureID
    0.63
    +#+#
    0.59
    ="@+
    0.58
     propOrder
    0.52
    AxisAlignment
    0.51
    enumi
    0.51
     IndexPath
    0.48
    లాలు
    0.48
    hmigung
    0.47
    IsContent
    0.47
    Act Density 0.056%

    No Known Activations