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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash

    The neuron specifically detects LaTeX document class declarations (the “\documentclass[…]{…}” preamble).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    stackpath
    -0.07
     eing
    -0.06
    =center
    -0.06
     městě
    -0.06
     Mé
    -0.06
     swingerclub
    -0.06
    整个
    -0.06
     ripped
    -0.06
     svat
    -0.06
     Abd
    -0.06
    POSITIVE LOGITS
    related
    0.07
     Various
    0.06
     jobId
    0.06
    ll
    0.06
     downturn
    0.06
    ัญ
    0.06
    covers
    0.06
     修改
    0.06
    _sql
    0.06
    'r
    0.06
    Act Density 0.000%

    No Known Activations