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

    Neuronpedia

    INDEX
    Explanations

    self-defense

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of taking a class or training, especially phrases like “self-defense class,” “resistance training,” or similar training contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     :-)
    -0.07
    "].
    -0.07
    _ta
    -0.06
    (foo
    -0.06
    Atl
    -0.06
    elik
    -0.06
    tz
    -0.06
     ماده
    -0.06
    	yield
    -0.06
     Ebook
    -0.06
    POSITIVE LOGITS
    χή
    0.07
    短
    0.06
     Illustrator
    0.06
     formulas
    0.06
    due
    0.06
     libero
    0.06
     основе
    0.06
    بول
    0.06
     insight
    0.06
     сопров
    0.06
    Act Density 0.008%

    No Known Activations