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

    Neuronpedia

    INDEX
    Explanations

    C code interrupt handlers

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric literals—especially floating‐point numbers—appearing in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    了解
    -0.07
    metadata
    -0.06
    人才
    -0.06
     BAS
    -0.06
    _PORTS
    -0.06
     هوش
    -0.06
    ’↵
    -0.06
     wann
    -0.06
    .Window
    -0.06
    erosis
    -0.06
    POSITIVE LOGITS
     apex
    0.07
     eventdata
    0.07
     accent
    0.07
     <!
    0.06
    рів
    0.06
     verilen
    0.06
    >:
    0.06
     kuvvet
    0.06
     Challenger
    0.06
     quo
    0.06
    Act Density 0.003%

    No Known Activations