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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects forum post metadata markers such as “Originally,” “Posted,” and “by” in quoted or re-posted entries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ']");↵
    -0.07
     lv
    -0.07
    .priority
    -0.07
     Improved
    -0.07
    -automatic
    -0.06
     liable
    -0.06
    MaxLength
    -0.06
    ipay
    -0.06
    ImagePath
    -0.06
    _IMP
    -0.06
    POSITIVE LOGITS
     firmly
    0.08
     unut
    0.06
    abler
    0.06
    ูล
    0.06
    <TResult
    0.06
    essen
    0.06
     цьому
    0.06
    issues
    0.06
    esen
    0.06
     Spear
    0.06
    Act Density 0.003%

    No Known Activations