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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals—especially digits and floating‐point numbers (e.g. the “2,4.73046875” style quantifier numbers in the regex).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     potent
    -0.06
    _whitespace
    -0.06
    collections
    -0.06
    ustr
    -0.06
    ереж
    -0.06
    277
    -0.06
    addComponent
    -0.06
     getir
    -0.06
    _zeros
    -0.06
    ріп
    -0.06
    POSITIVE LOGITS
    <decltype
    0.07
     andre
    0.07
     σει
    0.06
    _ALIGNMENT
    0.06
     tenure
    0.06
    (Il
    0.06
     ResourceType
    0.06
     Story
    0.06
    .comments
    0.06
    科技有限公司
    0.06
    Act Density 0.001%

    No Known Activations