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

    Neuronpedia

    INDEX
    Explanations

    closing parentheses and semicolons in code snippets

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

    Code or data structures

    np_acts-logits-general · gemini-2.0-flash

    end of code block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.51
     yet
    -0.45
    Württemberg
    -0.45
    preventDefault
    -0.44
    énération
    -0.43
     corresponding
    -0.42
    tifik
    -0.42
     returning
    -0.42
     whatever
    -0.41
    elen
    -0.41
    POSITIVE LOGITS
    +#+#
    1.15
    出版年
    1.06
     ProtoMessage
    0.94
    ագրություններ
    0.93
     disambiguazione
    0.90
    InjectAttribute
    0.88
    stateProvider
    0.86
     bezeichneter
    0.85
     nahilalakip
    0.85
    ]--;
    0.85
    Act Density 0.139%

    No Known Activations