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

    Neuronpedia

    INDEX
    Explanations

    references to placeholders or underscores, often indicating missing or unspecified information

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

    Incomplete or missing information

    np_acts-logits-general · gemini-2.0-flash

    placeholder for code or redacted text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     orgullo
    -0.39
     ventajas
    -0.37
    cookieParser
    -0.35
     confusión
    -0.35
     asamblea
    -0.34
     lección
    -0.33
     discriminación
    -0.33
     transferencia
    -0.33
    ArgumentParser
    -0.33
     discusión
    -0.32
    POSITIVE LOGITS
    webElement
    0.65
    ParallelGroup
    0.65
     
    0.62
    NameInMap
    0.60
    发表于
    0.59
     nahilalakip
    0.59
     Taktlose
    0.59
    SourceChecksum
    0.57
    WriteTagHelper
    0.56
    DockStyle
    0.56
    Act Density 1.065%

    No Known Activations