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

    Neuronpedia

    INDEX
    Explanations

    SQL commands and data type definitions

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

    SQL data types

    np_acts-logits-general · gemini-2.0-flash

    SQL data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.73
    ValueStyle
    -0.71
    enumii
    -0.70
    ScopeManager
    -0.68
     disambiguazione
    -0.67
    enumi
    -0.65
     Réponses
    -0.65
    RegressionTest
    -0.63
    AutoScale
    -0.62
    MouseAdapter
    -0.62
    POSITIVE LOGITS
     big
    0.61
     tiny
    0.55
    tiny
    0.55
    clo
    0.53
    BIG
    0.53
     BIG
    0.53
    small
    0.50
     clo
    0.50
     blobs
    0.50
     small
    0.50
    Act Density 0.262%

    No Known Activations