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

    Neuronpedia

    INDEX
    Explanations

    intellectual

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive (“dead”) and does not respond to any tokens in these examples.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _roles
    -0.07
     ourselves
    -0.07
     '*',
    -0.07
     wäre
    -0.06
     $('[
    -0.06
    ProgressBar
    -0.06
    navigationBar
    -0.06
     mají
    -0.06
    getService
    -0.06
    jour
    -0.06
    POSITIVE LOGITS
    Hip
    0.06
     intricate
    0.06
     Christina
    0.06
     приготовления
    0.06
    productive
    0.06
    /Sub
    0.06
    VEL
    0.06
     Tear
    0.06
    。（
    0.06
    람
    0.06
    Act Density 0.001%

    No Known Activations