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

    Neuronpedia

    INDEX
    Explanations

    numerical data and operations related to variables

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

    Hexadecimal code

    np_acts-logits-general · gemini-2.0-flash

    hex values assigned to constants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.83
     queſta
    -0.81
     Мексичка
    -0.80
    httphttps
    -0.79
     snippetHide
    -0.78
     виправивши
    -0.77
     ویکی‌پدی
    -0.77
    WriteTagHelper
    -0.75
    afficheront
    -0.74
     سكانية
    -0.73
    POSITIVE LOGITS
     
    0.51
     be
    0.44
     for
    0.44
     "
    0.43
     also
    0.42
     said
    0.42
     S
    0.42
     de
    0.41
     K
    0.41
     Chi
    0.41
    Act Density 0.382%

    No Known Activations