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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols, often used in mathematical or programming contexts

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

    Tokens enclosed in square brackets

    np_acts-logits-general · gemini-2.0-flash

    academic paper citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.49
     Bell
    -0.48
     sanitaires
    -0.47
     te
    -0.44
    ful
    -0.42
     con
    -0.41
    <
    -0.41
    ждую
    -0.41
    ddle
    -0.41
     alla
    -0.40
    POSITIVE LOGITS
    Personensuche
    1.13
     فريبيس
    1.08
    TagMode
    1.06
    StoryboardSegue
    0.96
     مشين
    0.96
    دانشنامهٔ
    0.95
    ImageContext
    0.92
     disambiguazione
    0.89
    AddTagHelper
    0.86
     bezeichneter
    0.81
    Act Density 0.005%

    No Known Activations