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

    Neuronpedia

    INDEX
    Explanations

    Providing information

    np_max-act · gemini-2.0-flash

    This neuron never activates on any tokens and thus does not detect or respond to any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    獲
    -0.07
    чем
    -0.06
     messagebox
    -0.06
    ']))
↵
    -0.06
     Vice
    -0.06
     들
    -0.06
     MAIN
    -0.06
    외
    -0.06
     omez
    -0.06
    toc
    -0.06
    POSITIVE LOGITS
     installs
    0.07
    rone
    0.07
     liquidity
    0.06
     è
    0.06
     renderer
    0.06
     areas
    0.06
    -lived
    0.06
    oleon
    0.06
     cinemat
    0.06
     πολύ
    0.06
    Act Density 0.019%

    No Known Activations