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

    Neuronpedia

    INDEX
    Explanations

    :image

    np_max-act · gemini-2.0-flash

    This neuron is essentially dead—it never activates on any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     đoạn
    -0.07
     triplet
    -0.06
    융
    -0.06
    arbon
    -0.06
    anager
    -0.06
    organized
    -0.06
    bai
    -0.06
    yses
    -0.06
     pessim
    -0.06
     transformations
    -0.06
    POSITIVE LOGITS
    :"",↵
    0.07
     возду
    0.07
    糖
    0.07
    =end
    0.06
    iostream
    0.06
    Lights
    0.06
     lái
    0.06
     رشته
    0.06
     DAR
    0.06
     лікар
    0.06
    Act Density 0.001%

    No Known Activations