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

    Neuronpedia

    INDEX
    Explanations

    Monetary values

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on numeric tokens—especially monetary amounts, percentages, and other financial figures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    MLElement
    -0.07
    公里
    -0.06
    Ion
    -0.06
    361
    -0.06
     cuent
    -0.06
     SECURITY
    -0.06
    -label
    -0.06
     seed
    -0.06
    pawn
    -0.06
    [len
    -0.05
    POSITIVE LOGITS
    =query
    0.07
     organizing
    0.07
     scarcely
    0.07
    Danger
    0.06
    _SPEC
    0.06
     hollow
    0.06
    .nn
    0.06
     jika
    0.06
     imageURL
    0.06
    Broad
    0.06
    Act Density 0.010%

    No Known Activations