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

    Neuronpedia

    INDEX
    Explanations

    abstracts

    np_max-act · gemini-2.0-flash

    The neuron is detecting the “abstract” section header in scientific‐paper markup.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Renders
    -0.07
    micro
    -0.06
    NSNotification
    -0.06
    епти
    -0.06
    prites
    -0.06
     {*
    -0.06
    tv
    -0.06
    PCI
    -0.06
    Spl
    -0.06
     fingert
    -0.06
    POSITIVE LOGITS
     yolc
    0.07
    .getFloat
    0.07
     uneven
    0.07
     cholesterol
    0.06
    Calculator
    0.06
    ้นท
    0.06
    يل
    0.06
    ivamente
    0.06
    dims
    0.06
    [length
    0.06
    Act Density 0.003%

    No Known Activations