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

    Neuronpedia

    INDEX
    Explanations

    mode

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the identifier “mode” (in various capitalizations) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     clusters
    -0.07
     crystals
    -0.07
     Birth
    -0.07
     trif
    -0.07
     visitor
    -0.07
    'ят
    -0.06
     Fruit
    -0.06
    	graph
    -0.06
     tooth
    -0.06
     insects
    -0.06
    POSITIVE LOGITS
    Mode
    0.16
     mode
    0.15
     modes
    0.14
    mode
    0.13
     Mode
    0.13
    _mode
    0.12
    .Mode
    0.11
    .mode
    0.11
     MODE
    0.11
    -mode
    0.11
    Act Density 0.020%

    No Known Activations