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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron fires on news‐style dateline and metadata tokens (e.g. city names with colons, parenthetical source tags, and date/time markers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	tx
    -0.07
    ような
    -0.06
     엔
    -0.06
     mocked
    -0.06
     ống
    -0.06
    iliz
    -0.06
     trad
    -0.06
     Typed
    -0.06
    ويل
    -0.06
    (active
    -0.06
    POSITIVE LOGITS
     görev
    0.07
    Gre
    0.07
     DPR
    0.06
    面积
    0.06
    _SEGMENT
    0.06
    -*
    0.06
     wrath
    0.06
    sk
    0.06
    ::|
    0.06
     consultancy
    0.06
    Act Density 0.206%

    No Known Activations