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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    енням
    -0.08
    .validator
    -0.07
     dbs
    -0.06
    include
    -0.06
    圳
    -0.06
    .Selected
    -0.06
    青
    -0.06
    ylinder
    -0.06
     반환
    -0.06
     paypal
    -0.06
    POSITIVE LOGITS
    raham
    0.07
     UT
    0.07
     das
    0.06
    _UTF
    0.06
     Juli
    0.06
    prung
    0.06
     Hillary
    0.06
     otra
    0.06
    phis
    0.06
     ferv
    0.06
    Act Density 0.055%

    No Known Activations