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

    Neuronpedia

    INDEX
    Explanations

    references to logging functionality in code

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

    log information SLF

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.60
    IndentedString
    -0.57
    TypedDataSet
    -0.57
     esternos
    -0.54
    ImageContext
    -0.52
    Tikang
    -0.48
     
    -0.47
    transQ
    -0.47
    >",
    -0.46
     noDo
    -0.46
    POSITIVE LOGITS
    Slf
    0.43
     المعيارى
    0.39
     encargado
    0.39
    MigrationBuilder
    0.39
    covo
    0.38
    cesz
    0.37
     encargada
    0.37
     leading
    0.36
     Allein
    0.36
     trata
    0.36
    Act Density 0.002%

    No Known Activations