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

    Neuronpedia

    INDEX
    Explanations

    statistics

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric tokens (especially decimal numbers), i.e. it finds numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Scoped
    -0.07
    333
    -0.07
     Cooper
    -0.07
    rve
    -0.07
     Snape
    -0.06
    OPER
    -0.06
    ่อง
    -0.06
     हव
    -0.06
    Operating
    -0.06
    -saving
    -0.06
    POSITIVE LOGITS
     <",
    0.06
    ___↵↵
    0.06
    $email
    0.06
    …↵
    0.06
    一点
    0.06
    LocalizedMessage
    0.06
     ∈
    0.06
    hek
    0.06
    ecom
    0.06
    .setState
    0.06
    Act Density 0.051%

    No Known Activations