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

    Neuronpedia

    INDEX
    Explanations

    machine learning datasets

    np_max-act · gemini-2.0-flash

    This neuron activates on passages describing data augmentation and similar sampling techniques in deep learning.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    455
    -0.07
    цент
    -0.06
    Modules
    -0.06
     位
    -0.06
    QRSTUVWXYZ
    -0.06
    urvey
    -0.06
    435
    -0.06
    ")]
    -0.06
    adle
    -0.06
     Cow
    -0.06
    POSITIVE LOGITS
    ,long
    0.07
     pardon
    0.07
    UILDER
    0.06
     adventurer
    0.06
    utilus
    0.06
     Stella
    0.06
     hiçbir
    0.06
     Somerset
    0.06
     abandon
    0.06
    _clicked
    0.06
    Act Density 0.017%

    No Known Activations