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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that occur as list‐item markers or list entries (e.g. after bullets or numbers), i.e. it identifies parts of enumerated or bulleted lists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cmp
    -0.07
     cannabis
    -0.06
    	buff
    -0.06
     seeker
    -0.06
    慎
    -0.06
    Fraction
    -0.06
    _dim
    -0.06
     мак
    -0.06
     realization
    -0.06
     near
    -0.06
    POSITIVE LOGITS
    [G
    0.07
    送料
    0.07
    ;<
    0.06
    .FileName
    0.06
     endors
    0.06
     طبي
    0.06
    }:${
    0.06
     RedirectToAction
    0.06
     ">
    0.06
    Cooldown
    0.06
    Act Density 0.024%

    No Known Activations