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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron primarily lights up on numerical tokens and quantitative expressions, picking out measurements, percentages, dates, and other numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _();↵
    -0.06
    usband
    -0.06
    (type
    -0.06
    ='#
    -0.06
    rides
    -0.06
    venience
    -0.06
    002
    -0.06
    Audit
    -0.06
    내기
    -0.06
     visa
    -0.06
    POSITIVE LOGITS
     devoid
    0.06
    .loadtxt
    0.06
     文章
    0.06
     precios
    0.06
    orWhere
    0.06
     learn
    0.06
     م
    0.06
     MARK
    0.06
    *S
    0.06
     iss
    0.06
    Act Density 0.070%

    No Known Activations