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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wor
    -0.09
    urovision
    -0.07
    ी)
    -0.07
     spanning
    -0.07
     proletariat
    -0.07
    #/
    -0.06
    ाओ
    -0.06
    ilo
    -0.06
     sc
    -0.06
     saldırı
    -0.06
    POSITIVE LOGITS
    Module
    0.07
     defaults
    0.07
    (selected
    0.07
    还
    0.06
    XmlElement
    0.06
     Recently
    0.06
     randomly
    0.06
     chắc
    0.06
     输出
    0.05
    Accessory
    0.05
    Act Density 0.004%

    No Known Activations