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

    Neuronpedia

    INDEX
    Explanations

    Not found

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literal tokens in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    redd
    -0.07
    ้อม
    -0.07
    pios
    -0.07
     Prosec
    -0.07
    ег
    -0.06
    ास
    -0.06
     sometimes
    -0.06
     strtolower
    -0.06
    ือก
    -0.06
     defiance
    -0.06
    POSITIVE LOGITS
     getType
    0.07
     helm
    0.06
     rave
    0.06
    ／/
    0.06
    using
    0.06
     backstage
    0.06
    )arg
    0.06
    ỡ
    0.06
     Verm
    0.06
     onHide
    0.06
    Act Density 0.018%

    No Known Activations