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

    Neuronpedia

    INDEX
    Explanations

    information related to research studies and their findings

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

    Percentages or fractions

    np_acts-logits-general · gemini-2.0-flash

    percentages and proportions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.80
    Filmografie
    -0.60
    enumi
    -0.50
    various
    -0.46
     resourceCulture
    -0.45
    IsContent
    -0.45
    jsonwebtoken
    -0.44
    Various
    -0.43
    ɚ
    -0.43
    LEncoder
    -0.43
    POSITIVE LOGITS
     majority
    1.60
     half
    1.59
     nearly
    1.50
    majority
    1.50
    Majority
    1.47
     Nearly
    1.45
     Majority
    1.40
    Nearly
    1.39
    Half
    1.38
    nearly
    1.35
    Act Density 0.907%

    No Known Activations