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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with legal or formal documentation

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

    filed under

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.58
     وتسجيلات
    -0.56
     bakgrund
    -0.54
     bahía
    -0.50
     argint
    -0.50
    ęgn
    -0.50
     muun
    -0.49
    īg
    -0.49
     bruja
    -0.49
    condido
    -0.49
    POSITIVE LOGITS
    
    0.42
    TestingModule
    0.40
    XmlAccessorType
    0.38
     funeral
    0.38
     mourners
    0.35
    fromnode
    0.35
    HomeAsUpEnabled
    0.33
     meeting
    0.33
    makeConstraints
    0.32
     meet
    0.32
    Act Density 0.001%

    No Known Activations