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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on numerical measurement values—especially floating-point numbers and related numeric expressions—in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    TestData
    -0.08
    _yield
    -0.07
     etmiştir
    -0.07
    NotFound
    -0.06
    müştür
    -0.06
    -query
    -0.06
    Dist
    -0.06
     redraw
    -0.06
    단체
    -0.06
     democracy
    -0.06
    POSITIVE LOGITS
     diag
    0.07
     eval
    0.06
     />\
    0.06
    .Tasks
    0.06
    ;">
↵
    0.06
    ุก
    0.06
     fName
    0.06
    いに
    0.06
    accumulate
    0.06
     Strength
    0.06
    Act Density 0.032%

    No Known Activations