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

    Neuronpedia

    INDEX
    Explanations

    IS

    np_max-act · gemini-2.0-flash

    The neuron fires on the occurrence of the word “dismissed” (i.e. when a court opinion is marked as dismissed).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     include
    -0.07
    荒
    -0.07
    活
    -0.06
    nehmer
    -0.06
     favoured
    -0.06
     مان
    -0.06
     наступ
    -0.06
    ']."
    -0.06
    :',
    -0.06
     performs
    -0.06
    POSITIVE LOGITS
    _Source
    0.07
     Existing
    0.07
     gg
    0.07
    ृष
    0.07
     Marathon
    0.06
     orth
    0.06
    	CG
    0.06
     slug
    0.06
    ımın
    0.06
     martin
    0.06
    Act Density 0.000%

    No Known Activations