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

    Neuronpedia

    INDEX
    Explanations

    precedent

    np_max-act · gemini-2.0-flash

    This neuron detects the boilerplate disclaimer language indicating that an appellate opinion is “not precedent” (i.e. non-precedential).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -girl
    -0.07
     ($
    -0.06
     Cyc
    -0.06
    (".",
    -0.06
     Chains
    -0.06
     energies
    -0.06
     Basically
    -0.06
    (fontSize
    -0.06
     comments
    -0.06
     jail
    -0.06
    POSITIVE LOGITS
    	assertNotNull
    0.07
     prepend
    0.06
     argv
    0.06
    ā
    0.06
     커
    0.06
     b
    0.06
    Compute
    0.06
    appen
    0.06
    _WS
    0.06
    hev
    0.06
    Act Density 0.001%

    No Known Activations