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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating compliance with standards or ranges

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

    positional boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grüsse
    -0.54
     initComponents
    -0.48
    CloseOperation
    -0.47
     miniaturka
    -0.47
     thiệu
    -0.47
    úblico
    -0.44
     ainfi
    -0.42
     varandra
    -0.41
     Unterscheidung
    -0.41
     rechange
    -0.40
    POSITIVE LOGITS
     below
    0.48
     exceed
    0.48
     outside
    0.48
    ∉
    0.45
     <=",
    0.45
    ControllerAdvice
    0.44
     beyond
    0.44
     exceeding
    0.43
     exceeds
    0.43
     Outside
    0.42
    Act Density 0.307%

    No Known Activations