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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literal tokens (e.g. immediate values and constants) in code or disassembly.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Pie
    -0.07
     下
    -0.07
    overlay
    -0.06
    frame
    -0.06
    ۱۵
    -0.06
     drop
    -0.06
    ULLET
    -0.06
    country
    -0.06
    King
    -0.06
     spec
    -0.06
    POSITIVE LOGITS
    -custom
    0.06
     khả
    0.06
    ）:
    0.06
    [...,
    0.06
    (contents
    0.06
    ().'/
    0.06
    Asian
    0.06
     Robotics
    0.06
     προς
    0.06
    -lasting
    0.06
    Act Density 0.002%

    No Known Activations