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

    Neuronpedia

    INDEX
    Explanations

    Medical exclusions

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical tokens (e.g. measurements, statistics, and other digits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Adresse
    -0.07
    Sony
    -0.07
     openings
    -0.06
    왕
    -0.06
    foreground
    -0.06
     Best
    -0.06
    ，被
    -0.06
     kå
    -0.06
    scanner
    -0.06
    兴
    -0.06
    POSITIVE LOGITS
     embodiments
    0.07
     IA
    0.07
    .exceptions
    0.06
     '$
    0.06
     Image
    0.06
    .ant
    0.06
    ease
    0.06
     wrappers
    0.06
    icina
    0.06
    asons
    0.06
    Act Density 0.012%

    No Known Activations