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

    Neuronpedia

    INDEX
    Explanations

    references to legal or formal situations involving obligations and responsibilities

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

    subjects and auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.51
     defaultstate
    -0.49
    AutoScaleMode
    -0.47
    makeConstraints
    -0.46
    complexType
    -0.45
    RegistryLite
    -0.45
    ThemeOverlay
    -0.42
    RotationOrder
    -0.41
    GeneratedMessage
    -0.41
    RTSC
    -0.41
    POSITIVE LOGITS
     przecież
    0.69
     disambiguazione
    0.53
     surely
    0.44
     immerhin
    0.43
     Мексичка
    0.42
    这么多
    0.42
    だし
    0.41
     potuto
    0.41
     Schließlich
    0.41
     tantos
    0.40
    Act Density 0.126%

    No Known Activations