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

    Neuronpedia

    INDEX
    Explanations

    Particle physics

    np_max-act · gemini-2.0-flash

    the neuron activates on words that are names of particles ending in “-on” (e.g. photon, meson, pion, kaon).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     valley
    -0.07
     hairstyle
    -0.06
     wireType
    -0.06
    Providers
    -0.06
    ource
    -0.06
     میزان
    -0.06
     سبتمبر
    -0.06
    porno
    -0.06
     程
    -0.06
     женщины
    -0.06
    POSITIVE LOGITS
    bread
    0.07
    Ignore
    0.07
     kl
    0.07
    전
    0.06
     concentr
    0.06
    ff
    0.06
    وسف
    0.06
     renewable
    0.06
    自動
    0.06
     tái
    0.06
    Act Density 0.002%

    No Known Activations