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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens representing computed values—especially floating-point numbers—in calculation steps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     arrog
    -0.07
     wk
    -0.06
    input
    -0.06
     offices
    -0.06
    今年
    -0.06
     antibiot
    -0.06
     PIXEL
    -0.06
    いる
    -0.06
     lymph
    -0.05
     month
    -0.05
    POSITIVE LOGITS
    ß
    0.07
    _:
    0.06
     Miner
    0.06
     modulo
    0.06
    sequence
    0.06
     setters
    0.06
     М
    0.06
    move
    0.06
    quires
    0.06
     heed
    0.06
    Act Density 0.038%

    No Known Activations