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

    Neuronpedia

    INDEX
    Explanations

    yards

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal‐formatted numeric tokens (i.e. fractional numbers in statistics).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     six
    -0.07
    _intersect
    -0.06
    four
    -0.06
    Profiles
    -0.06
    ेकर
    -0.06
    -two
    -0.06
    zeichnet
    -0.06
    )!
    -0.06
     Reads
    -0.06
    -suite
    -0.06
    POSITIVE LOGITS
     جم
    0.07
     yard
    0.07
     Michigan
    0.07
     відб
    0.07
     Avery
    0.07
     hvordan
    0.07
    اة
    0.07
     Accident
    0.07
    ыт
    0.06
     waters
    0.06
    Act Density 0.001%

    No Known Activations