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

    Neuronpedia

    INDEX
    Explanations

    grammar

    np_max-act · gemini-2.0-flash

    This neuron detects list or section markers—especially numbered items and tense headings (e.g. “1,” “2,” “Present,” “Past,” “Future”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (delay
    -0.07
     setter
    -0.07
    COD
    -0.06
     NEGLIGENCE
    -0.06
     gou
    -0.06
    Hop
    -0.06
     конечно
    -0.06
     практически
    -0.06
    beck
    -0.06
     Prior
    -0.06
    POSITIVE LOGITS
     Şimdi
    0.07
     FG
    0.07
    阅读
    0.06
     haystack
    0.06
    \HttpFoundation
    0.06
    etCode
    0.06
    ▍▍
    0.06
    (hist
    0.06
    ?↵↵↵↵↵↵
    0.06
     účin
    0.06
    Act Density 0.005%

    No Known Activations