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

    Neuronpedia

    INDEX
    Explanations

    labyrinth

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numbers (decimal values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     الصن
    -0.07
     مختصات
    -0.07
    祖
    -0.07
     ttl
    -0.07
     �
    -0.06
     SERIAL
    -0.06
    _rb
    -0.06
    ungalow
    -0.06
    Serial
    -0.06
    <O
    -0.06
    POSITIVE LOGITS
     labyrinth
    0.12
     maze
    0.11
     Maze
    0.10
     COVID
    0.08
    abyrin
    0.08
    	grid
    0.07
     Matrix
    0.07
     Haven
    0.07
     complex
    0.07
     lord
    0.07
    Act Density 0.002%

    No Known Activations