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

    Neuronpedia

    INDEX
    Explanations

    blogger tags and comments

    np_max-act · gemini-2.0-flash

    The neuron is triggered by long multi‐digit numeric tokens (e.g. blog post IDs, timestamps, and extended number strings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Shows
    -0.07
    吾
    -0.06
    -C
    -0.06
    .IsNullOr
    -0.06
     Gra
    -0.06
     CLEAR
    -0.06
     [
    -0.06
     peaceful
    -0.06
     simp
    -0.06
    imbus
    -0.06
    POSITIVE LOGITS
    еления
    0.06
     Founded
    0.06
    表示
    0.06
     프로
    0.06
    .LocalDate
    0.06
    abstract
    0.06
     aproxim
    0.06
     стро
    0.06
    iesta
    0.06
     reporting
    0.06
    Act Density 0.003%

    No Known Activations