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

    Neuronpedia

    INDEX
    Explanations

    ID numbers and codes

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect sequences of digits (numeric codes, amounts, dates, and other multi‐digit numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    िद
    -0.07
    Bound
    -0.06
    і
    -0.06
    Bed
    -0.06
    _slide
    -0.06
    Kick
    -0.06
    ulum
    -0.06
    ила
    -0.06
    ID
    -0.06
    ترنت
    -0.06
    POSITIVE LOGITS
     أس
    0.07
    ’aut
    0.06
     disclaimer
    0.06
    各种
    0.06
    _GRE
    0.06
    'aut
    0.06
     Levine
    0.06
     محصولات
    0.06
    _Status
    0.06
    <p
    0.06
    Act Density 0.008%

    No Known Activations