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

    Neuronpedia

    INDEX
    Explanations

    technical terms and measurements often used in scientific analysis

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

    Characters or symbols followed by commas or brackets

    np_acts-logits-general · gemini-2.0-flash

    letters, numbers, abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.90
     GenerationType
    -0.89
     فريبيس
    -0.83
    BufferException
    -0.81
    ьажоргаш
    -0.81
    DockStyle
    -0.80
     للاسماء
    -0.77
    SBATCH
    -0.72
    AddTagHelper
    -0.72
    ंदीखरीदारी
    -0.71
    POSITIVE LOGITS
    はこちら
    0.31
     Оно
    0.30
    はコチラ
    0.24
     yerine
    0.23
    ตรี
    0.23
    のですね
    0.23
     etc
    0.23
    aspetto
    0.22
    side
    0.22
     оно
    0.22
    Act Density 0.334%

    No Known Activations