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

    Neuronpedia

    INDEX
    Explanations

    track

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens representing numeric or ordered-list markers—e.g. years, chapter/section numbers, Roman numerals, page numbers, and similar enumeration labels.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     crunchy
    -0.07
     wig
    -0.07
     creators
    -0.07
     Modifier
    -0.07
    /student
    -0.07
     strings
    -0.07
    Vue
    -0.07
    ymce
    -0.06
    ocument
    -0.06
     plus
    -0.06
    POSITIVE LOGITS
    odní
    0.07
     گیری
    0.06
     складі
    0.06
    .Mock
    0.06
    �
    0.06
    飞
    0.06
     місцев
    0.06
     حتی
    0.06
    childs
    0.06
    于是
    0.06
    Act Density 1.423%

    No Known Activations