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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron fires on technical specification tokens—parameter names, numeric values, units, and dimension labels in spec lists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ступ
    -0.07
     mně
    -0.07
     scrub
    -0.07
     rulers
    -0.06
    Sony
    -0.06
     Tab
    -0.06
     servants
    -0.06
    _documents
    -0.06
     sessionStorage
    -0.06
    Marker
    -0.06
    POSITIVE LOGITS
    [R
    0.07
     рік
    0.07
     presidents
    0.07
     vk
    0.06
    0.06
    ],&
    0.06
    0.06
     か
    0.06
     Depart
    0.06
    .i
    0.06
    Act Density 0.065%

    No Known Activations