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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Memphis
    -0.08
    xAF
    -0.07
    率达到
    -0.07
     Tin
    -0.07
     CORS
    -0.07
     Ren
    -0.07
     Triumph
    -0.07
    .Timeout
    -0.07
     một
    -0.07
    <Route
    -0.06
    POSITIVE LOGITS
    �
    0.07
    (chat
    0.07
    俺
    0.07
    olan
    0.07
     layered
    0.07
    离子
    0.06
    事宜
    0.06
    כא
    0.06
     Boris
    0.06
    зд
    0.06
    Act Density 0.002%

    No Known Activations