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

    Neuronpedia

    INDEX
    Explanations

    patterns of whitespace and indentation in code

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

    implementation_type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.47
     Segurança
    -0.39
    pantalón
    -0.38
    ainville
    -0.38
     saco
    -0.37
    Ƚ
    -0.37
    üyor
    -0.36
     réforme
    -0.36
    Ārējās
    -0.36
     dAtA
    -0.36
    POSITIVE LOGITS
    awtextra
    0.68
    InjectAttribute
    0.50
    GraphicsUnit
    0.47
     كومونز
    0.47
    hoeddwyd
    0.47
     yyr
    0.46
    okhttp
    0.46
     uſed
    0.44
     autorytatywna
    0.44
    awaiter
    0.43
    Act Density 0.001%

    No Known Activations