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

    Neuronpedia

    INDEX
    Explanations

    Code and website setup

    np_max-act · gemini-2.0-flash

    This neuron detects user requests or questions about running, installing, deploying, or executing the model locally on their own computer.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Breakfast
    -0.07
     Oh
    -0.07
     للح
    -0.06
    WAIT
    -0.06
    _SPE
    -0.06
    ée
    -0.06
    ื
    -0.06
    ё
    -0.06
    oreferrer
    -0.06
     سل
    -0.06
    POSITIVE LOGITS
     kvinder
    0.07
    .setPositiveButton
    0.07
     returnValue
    0.06
     时间
    0.06
     Pří
    0.06
     vrou
    0.06
    .Auto
    0.06
     Timeline
    0.06
    ItemClick
    0.06
    OptionsResolver
    0.06
    Act Density 0.054%

    No Known Activations