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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    defines
    -0.08
     dve
    -0.08
     damning
    -0.07
     şi
    -0.06
    dummy
    -0.06
    coupon
    -0.06
    Url
    -0.06
    穴
    -0.06
     Bits
    -0.06
    اده
    -0.06
    POSITIVE LOGITS
     аналіз
    0.07
     янва
    0.06
    _MAY
    0.06
     organising
    0.06
    .temp
    0.06
     Plantae
    0.06
     rég
    0.06
    кта
    0.06
    Không
    0.06
    ικοί
    0.06
    Act Density 0.039%

    No Known Activations