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

    Neuronpedia

    INDEX
    Explanations

    "//"

    np_max-act · gemini-2.0-flash

    The neuron fires on decimal numbers appearing in comments (e.g. floating‐point values like “4.3125” in “// 4.3125”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lique
    -0.06
    -0.06
    (Render
    -0.06
    	pl
    -0.06
     Зап
    -0.06
     mav
    -0.06
    -0.06
     ItemType
    -0.06
    _updated
    -0.06
     hockey
    -0.06
    POSITIVE LOGITS
     Türk
    0.07
     undesirable
    0.06
     Alternate
    0.06
     Nonetheless
    0.06
     Forum
    0.06
    озможно
    0.06
     bulls
    0.06
    ฑ
    0.06
     organizace
    0.06
    ΗΝ
    0.06
    Act Density 0.003%

    No Known Activations