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

    Neuronpedia

    INDEX
    Explanations

    few

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on decimal numeric values (floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     توانید
    -0.07
    уля
    -0.06
    -widgets
    -0.06
     wastes
    -0.06
    르는
    -0.06
    (Return
    -0.06
    》（
    -0.06
    _packet
    -0.06
    丽
    -0.06
    oves
    -0.06
    POSITIVE LOGITS
     Montgomery
    0.07
    246
    0.07
     مرح
    0.07
    ,[
    0.07
    طب
    0.06
    itemName
    0.06
    itom
    0.06
    PackageName
    0.06
    _med
    0.06
     shader
    0.06
    Act Density 0.015%

    No Known Activations