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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    This neuron detects the docket‐number portions of legal case citations (e.g. “CR-08-1102”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Restrictions
    -0.07
    так
    -0.07
     dù
    -0.07
     accuses
    -0.07
     cambio
    -0.06
     violated
    -0.06
     studied
    -0.06
    _TLS
    -0.06
    	let
    -0.06
    ')}}"
    -0.06
    POSITIVE LOGITS
    _numer
    0.07
    <Any
    0.07
     сух
    0.07
    xmin
    0.07
    -D
    0.06
    -p
    0.06
    -West
    0.06
     Holmes
    0.06
     mund
    0.06
     υπ
    0.06
    Act Density 0.003%

    No Known Activations