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

    Neuronpedia

    INDEX
    Explanations

    oxide

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens and measurements (digits, numbers, and related units) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Cb
    -0.06
     indir
    -0.06
    .AddItem
    -0.06
     CHR
    -0.06
     qr
    -0.06
     a
    -0.06
     slammed
    -0.06
    .sz
    -0.06
    dateFormat
    -0.06
    _rq
    -0.06
    POSITIVE LOGITS
    atural
    0.07
    esty
    0.07
     Aleks
    0.07
    ardo
    0.06
     serotonin
    0.06
    Alle
    0.06
     ij
    0.06
    UTION
    0.06
    -peer
    0.06
    _race
    0.06
    Act Density 0.001%

    No Known Activations