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

    Neuronpedia

    INDEX
    Explanations

    Code compilation

    np_max-act · gemini-2.0-flash

    This neuron activates on image-preprocessing code—specifically calls that resize image tensors and normalize their pixel values (e.g. tf.image.resize(...)/255.0).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     เต
    -0.07
     HttpStatusCode
    -0.07
    .scheme
    -0.06
    InputChange
    -0.06
    ffect
    -0.06
    Pří
    -0.06
     Saturdays
    -0.06
     routine
    -0.06
     Feel
    -0.06
     Shelf
    -0.06
    POSITIVE LOGITS
     عفش
    0.07
     Кар
    0.06
     ﻣ
    0.06
    theorem
    0.06
    -defined
    0.06
     Kag
    0.06
     καὶ
    0.06
     theorem
    0.06
     рес
    0.06
    (baseUrl
    0.06
    Act Density 0.003%

    No Known Activations