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

    Neuronpedia

    INDEX
    Explanations

    dot

    np_max-act · gemini-2.0-flash

    technical jargon and terminology related to programming and software development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron specifically responds to numeric tokens representing decimal or floating-point values (e.g. “.2216796875”, “1.98828125”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     AM
    -0.07
     onwards
    -0.07
     پروژه
    -0.06
    itelist
    -0.06
    	player
    -0.06
    -workers
    -0.06
    アニメ
    -0.06
     술
    -0.06
     journeys
    -0.06
    _attempts
    -0.06
    POSITIVE LOGITS
    數
    0.08
     [('
    0.07
    (tokens
    0.07
     [("
    0.07
     [(
    0.07
    (Symbol
    0.07
     jednotliv
    0.07
    empor
    0.06
    yps
    0.06
    .addRow
    0.06
    Act Density 0.002%

    No Known Activations