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    The neuron fires on the “is not precedent” boilerplate—i.e. it detects the “is not” in the non-precedential notice.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ovými
    -0.07
     صورت
    -0.07
    与
    -0.06
     راه
    -0.06
    吴
    -0.06
     कहन
    -0.06
     히
    -0.06
    buscar
    -0.06
    .／
    -0.06
     与
    -0.06
    POSITIVE LOGITS
    .Evaluate
    0.07
    ugal
    0.07
     suggests
    0.07
    @app
    0.07
    (List
    0.07
    (fullfile
    0.07
     Previous
    0.06
     subsequent
    0.06
     classy
    0.06
     true
    0.06
    Act Density 0.001%

    No Known Activations