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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash

    The neuron is selectively spotting numeric tokens (digits and decimal numbers) embedded in the math/LaTeX expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .:.:.:
    -0.08
     úřad
    -0.07
    mailer
    -0.07
    开展
    -0.06
     anxiety
    -0.06
     podem
    -0.06
    -loader
    -0.06
    Nation
    -0.06
    780
    -0.06
     mano
    -0.06
    POSITIVE LOGITS
    ::{↵
    0.06
     مستق
    0.06
    _insn
    0.06
     Operational
    0.06
     dred
    0.06
    lod
    0.06
    ีช
    0.06
     wicht
    0.06
     automát
    0.06
    											↵
    0.06
    Act Density 0.026%

    No Known Activations