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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated characters

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

    user declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.54
    Diwedd
    -0.54
    évaluateur
    -0.54
     мәкал
    -0.49
     بيها
    -0.48
    ंदीखरीदारी
    -0.45
    hoeddwyd
    -0.45
    Халык
    -0.45
    Transkript
    -0.44
     kasarigan
    -0.44
    POSITIVE LOGITS
    featureID
    0.46
    DebuggerNonUser
    0.45
    elemField
    0.42
    enterOuterAlt
    0.42
    stateProvider
    0.42
    endregion
    0.42
    QMetaType
    0.41
    Eloquent
    0.40
     propOrder
    0.40
    PropertyChanging
    0.40
    Act Density 0.002%

    No Known Activations