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

    Neuronpedia

    INDEX
    Explanations

    phrases related to research and experimental study methods

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

    Tokens followed by commas

    np_acts-logits-general · gemini-2.0-flash

    similarly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.90
     للاسماء
    -0.84
    awtextra
    -0.83
     الاطلاع
    -0.82
     newBuilder
    -0.81
    Rujuakan
    -0.81
     '\\;'
    -0.81
    ArgsConstructor
    -0.79
     Paglinawan
    -0.79
    RectangleBorder
    -0.78
    POSITIVE LOGITS
     ebenfalls
    0.88
    同じく
    0.79
     szint
    0.76
     тоже
    0.73
    こちらも
    0.72
    ditto
    0.70
     invece
    0.70
     likewise
    0.70
    同上
    0.69
     similarly
    0.68
    Act Density 2.770%

    No Known Activations