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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capability or possibility

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

    Auxiliary verbs (been, can, be, did, was)

    np_acts-logits-general · gemini-2.0-flash

    past tense verbs and modals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.69
    ContentAsync
    -0.67
    ThroughAttribute
    -0.65
    HasForeignKey
    -0.61
    Weblinks
    -0.57
    中略
    -0.55
     Recover
    -0.55
    _));
    -0.54
     Efq
    -0.54
     transférez
    -0.54
    POSITIVE LOGITS
    السكان
    0.56
    WebVitals
    0.53
     NSError
    0.52
    AsUp
    0.52
     stronie
    0.51
    instancetype
    0.50
     puesta
    0.48
     being
    0.48
     ביום
    0.48
    ActionCreators
    0.48
    Act Density 0.449%

    No Known Activations