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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    This neuron highlights numeric tokens (digits and decimal numbers) within the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     acoustic
    -0.07
     два
    -0.07
    22
    -0.07
     Edge
    -0.07
     INTERVAL
    -0.06
     incorporates
    -0.06
    ач
    -0.06
     examples
    -0.06
     pul
    -0.06
    applications
    -0.06
    POSITIVE LOGITS
    _LEFT
    0.07
    นท
    0.06
    [__
    0.06
     torrent
    0.05
     کو
    0.05
    venient
    0.05
    <iostream
    0.05
     boyut
    0.05
     yapıyor
    0.05
     مختصات
    0.05
    Act Density 0.067%

    No Known Activations