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

    Neuronpedia

    INDEX
    Explanations

    elements related to user interface components in a coding environment

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

    Code snippets and formatting elements

    np_acts-logits-general · gemini-2.0-flash

    Transformer code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ostavi
    -0.53
     mineures
    -0.50
    PyExc
    -0.50
    TextAppearance
    -0.49
    Бахар
    -0.48
    ="../../
    -0.47
    Ссылки
    -0.47
    urbation
    -0.47
    ernalia
    -0.45
    SocketChannel
    -0.45
    POSITIVE LOGITS
     EconPapers
    0.66
     style
    0.61
    FunctionFlags
    0.59
    tangentMode
    0.55
     méthode
    0.55
     Waray
    0.55
     chi̍t
    0.54
     Style
    0.51
    style
    0.50
    Referanser
    0.50
    Act Density 0.098%

    No Known Activations