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

    Neuronpedia

    INDEX
    Explanations

    symbols or characters often used in programming or markup languages

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

    comment separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inSlope
    -0.74
     EconPapers
    -0.61
     المعيارى
    -0.60
    AndEndTag
    -0.59
     transfieras
    -0.59
     للمعارف
    -0.57
    SharedDtor
    -0.57
    :✨
    -0.56
     незавершена
    -0.55
    richTextPanel
    -0.54
    POSITIVE LOGITS
    ↵↵
    0.51
    DockStyle
    0.49
    */
    0.46
    AnchorStyles
    0.45
     Fran
    0.44
     Frank
    0.43
                             
    0.42
    version
    0.42
            
    0.42
     Far
    0.41
    Act Density 0.037%

    No Known Activations