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

    Neuronpedia

    INDEX
    Explanations

    code fragments

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on tokens that are parts of hexadecimal numeric literals (e.g. the “0”, “x”, and hex‐digit sequences in “0xNN”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Lines
    -0.06
    ﻠ
    -0.06
    rane
    -0.06
    ạp
    -0.06
    ē
    -0.06
    人才
    -0.06
    isc
    -0.06
     한번
    -0.06
    Acceleration
    -0.06
     Odyssey
    -0.06
    POSITIVE LOGITS
    amines
    0.07
     thắng
    0.06
    .setImage
    0.06
    _links
    0.06
    $_
    0.06
     radio
    0.06
    _agents
    0.06
    ارب
    0.06
    seller
    0.06
     فبراير
    0.06
    Act Density 0.008%

    No Known Activations