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

    Neuronpedia

    INDEX
    Explanations

    000

    np_max-act · gemini-2.0-flash

    This neuron fires on the first token of new sentences or major sections—i.e. sentence-initial words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .sky
    -0.07
     Lease
    -0.07
    Size
    -0.07
    Stan
    -0.06
     surrogate
    -0.06
    erialized
    -0.06
     شي
    -0.06
     ^{[
    -0.06
     [@
    -0.06
    address
    -0.06
    POSITIVE LOGITS
    ":"","
    0.06
     Ông
    0.06
    (ns
    0.06
    ImageSharp
    0.06
    ugging
    0.06
    .PARAM
    0.06
     researching
    0.06
     supplementary
    0.06
    ##_
    0.06
     postup
    0.06
    Act Density 0.032%

    No Known Activations