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

    Neuronpedia

    INDEX
    Explanations

    pragma

    np_max-act · gemini-2.0-flash

    The neuron strongly reacts to numeric literal tokens (especially floating‐point constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     robotic
    -0.07
    osh
    -0.06
    enské
    -0.06
     giống
    -0.06
    [:
    -0.06
     wounded
    -0.06
     outspoken
    -0.06
    /helpers
    -0.06
    _basis
    -0.06
    362
    -0.06
    POSITIVE LOGITS
     schnell
    0.08
    WithEmail
    0.07
     어디
    0.06
    _ANDROID
    0.06
     intending
    0.06
     Shops
    0.06
    HE
    0.06
    ضل
    0.06
    -www
    0.06
     درباره
    0.06
    Act Density 0.014%

    No Known Activations