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

    Neuronpedia

    INDEX
    Explanations

    programming language import statements

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

    code utilities and language imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FetchType
    -0.54
     Roskov
    -0.53
     lenker
    -0.52
    setVerticalGroup
    -0.50
    twimg
    -0.48
     defaultstate
    -0.46
    AsUp
    -0.45
    migrationBuilder
    -0.45
    addCriterion
    -0.43
    󠁴
    -0.43
    POSITIVE LOGITS
    共通
    0.53
     utilities
    0.47
     Utils
    0.46
    工具类
    0.44
     utils
    0.43
     util
    0.43
    utili
    0.43
     invokingState
    0.42
    utils
    0.41
     utility
    0.41
    Act Density 0.002%

    No Known Activations