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 is essentially inactive (“dead”) and does not respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ngũ
    -0.07
    .Element
    -0.06
     giảng
    -0.06
    트
    -0.06
    _BAD
    -0.06
     этот
    -0.06
    Fabric
    -0.06
     곳
    -0.06
    fork
    -0.06
     Darling
    -0.06
    POSITIVE LOGITS
    apa
    0.07
    주소
    0.07
     pcl
    0.07
    itizer
    0.06
    ürnberg
    0.06
    :path
    0.06
    oon
    0.06
     enrichment
    0.06
     JSX
    0.06
    :j
    0.06
    Act Density 0.071%

    No Known Activations