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

    Neuronpedia

    INDEX
    Explanations

    emails

    np_max-act · gemini-2.0-flash

    The neuron chiefly activates on tokens related to requesting or describing instructions and steps for submitting paperwork or using a website.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ули
    -0.08
    нє
    -0.07
    Site
    -0.06
     Воз
    -0.06
    ють
    -0.06
    WT
    -0.06
    River
    -0.06
     Hoàng
    -0.06
     навіть
    -0.06
     Chúa
    -0.06
    POSITIVE LOGITS
     eser
    0.07
    Lie
    0.07
     사실
    0.07
     december
    0.07
     MySQL
    0.06
    (rd
    0.06
    .CurrentRow
    0.06
     togg
    0.06
    .setDescription
    0.06
    .ReLU
    0.06
    Act Density 0.029%

    No Known Activations