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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting numeric tokens—especially counts and other numerical references—in legal‐style documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    subnet
    -0.07
     Delta
    -0.06
    ých
    -0.06
    unky
    -0.06
     Intersection
    -0.06
    quivo
    -0.06
    ští
    -0.06
    .a
    -0.06
     menos
    -0.06
    Frozen
    -0.06
    POSITIVE LOGITS
    thood
    0.06
    raised
    0.06
    沉
    0.06
    =”
    0.06
     draw
    0.06
    estimate
    0.06
    반
    0.06
     evacuated
    0.06
    人民共和国
    0.06
     classified
    0.06
    Act Density 0.002%

    No Known Activations