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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numeric tokens (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Anna
    -0.06
    .isFile
    -0.06
     Rey
    -0.06
    	Button
    -0.06
    /grpc
    -0.06
    urm
    -0.06
    mob
    -0.06
     Webb
    -0.06
    DeltaTime
    -0.06
    .gnu
    -0.06
    POSITIVE LOGITS
    ”—
    0.06
    Percent
    0.06
    Before
    0.06
     tableLayoutPanel
    0.06
    bows
    0.06
    _WH
    0.06
    StateChanged
    0.06
     imu
    0.06
     nz
    0.06
    [OF
    0.06
    Act Density 0.054%

    No Known Activations