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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    This neuron detects fragments of formal legal citations—e.g. statute or code section numbers and related markers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .prepend
    -0.07
    strconv
    -0.07
     prey
    -0.06
     loved
    -0.06
    esiz
    -0.06
    	utils
    -0.06
    řiv
    -0.06
    (rect
    -0.06
     superb
    -0.06
     خلف
    -0.06
    POSITIVE LOGITS
    规模
    0.07
    ------------
    0.06
    ActionBar
    0.06
     Fishing
    0.06
    ..........
    0.06
     Asked
    0.06
     non
    0.06
    _PROTOCOL
    0.06
     Strateg
    0.06
     ideally
    0.06
    Act Density 0.022%

    No Known Activations