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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    This neuron detects the names of the judges (and related panel attributions) in appellate court opinions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Harr
    -0.07
    ับปร
    -0.07
    	w
    -0.06
    	Message
    -0.06
     IX
    -0.06
    сок
    -0.06
    _acc
    -0.06
     Viv
    -0.06
    Beer
    -0.06
    /files
    -0.06
    POSITIVE LOGITS
     и
    0.07
     (!$
    0.07
    ournaments
    0.06
     zahrn
    0.06
    OUCH
    0.06
    にと
    0.06
     đâu
    0.06
     PVOID
    0.06
    لط
    0.06
    ő
    0.06
    Act Density 0.003%

    No Known Activations