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

    Neuronpedia

    INDEX
    Explanations

    code and text processing

    np_max-act · gemini-2.0-flash

    This neuron activates on code dealing with text‐to‐sequence preprocessing—i.e. the steps that convert and pad raw text into numerical sequences for a Keras model.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code related to natural language processing tasks using Keras.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Araştır
    -0.08
     Rockies
    -0.08
    Dst
    -0.07
    ницу
    -0.06
     myocard
    -0.06
    ♡
    -0.06
    очь
    -0.06
    floating
    -0.06
    Keyboard
    -0.06
    :::|
    -0.06
    POSITIVE LOGITS
     Ses
    0.07
    tion
    0.07
     tentative
    0.06
    Configurer
    0.06
    .swing
    0.06
     Slack
    0.06
    .distance
    0.06
    .iteritems
    0.06
     withdrawn
    0.06
     registrazione
    0.06
    Act Density 0.001%

    No Known Activations