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

    Neuronpedia

    INDEX
    Explanations

    patents

    np_max-act · gemini-2.0-flash

    The neuron detects numeric financial expressions—especially percentages and large currency amounts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    olson
    -0.06
    pection
    -0.06
    ference
    -0.06
     dataType
    -0.06
    染
    -0.06
     با
    -0.06
    .members
    -0.06
     μεγ
    -0.06
    ly
    -0.06
    PL
    -0.06
    POSITIVE LOGITS
    ενοδο
    0.08
     Halo
    0.07
    .".
    0.06
    'label
    0.06
     Listing
    0.06
     ihren
    0.06
    first
    0.06
     arreglo
    0.06
    兩
    0.06
    -click
    0.06
    Act Density 0.473%

    No Known Activations