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

    Neuronpedia

    INDEX
    Explanations

    neural network code

    np_max-act · gemini-2.0-flash

    code snippets related to defining and utilizing learning rate schedules in machine learning frameworks.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rlen
    -0.07
    xbe
    -0.07
     A
    -0.07
     Rud
    -0.06
    ينات
    -0.06
     flour
    -0.06
    interrupt
    -0.06
    _input
    -0.06
     progressDialog
    -0.06
     이미지
    -0.06
    POSITIVE LOGITS
     ―
    0.07
     환
    0.07
    lua
    0.07
     irresist
    0.07
     گیرد
    0.06
    时代
    0.06
     сна
    0.06
     знаход
    0.06
     협
    0.06
     розта
    0.06
    Act Density 0.008%

    No Known Activations