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

    Neuronpedia

    INDEX
    Explanations

    Timestamps

    np_max-act · gemini-2.0-flash

    This neuron identifies timestamp elements (numbers and punctuation) in subtitle timecodes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Mits
    -0.07
    :///
    -0.07
     fast
    -0.07
    ικού
    -0.07
    (transform
    -0.06
     �
    -0.06
    uture
    -0.06
     Trends
    -0.06
     Defaults
    -0.06
     Indones
    -0.06
    POSITIVE LOGITS
     rom
    0.08
    avity
    0.06
     tenure
    0.06
     inlet
    0.06
    _increment
    0.06
    \Entities
    0.06
    歲
    0.06
     zpracování
    0.06
     dří
    0.06
     داستان
    0.06
    Act Density 0.013%

    No Known Activations