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

    Neuronpedia

    INDEX
    Explanations

    scientific abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getState
    -0.06
     берем
    -0.06
    :num
    -0.06
     dressed
    -0.05
     Honey
    -0.05
     Pandora
    -0.05
    icy
    -0.05
     AZ
    -0.05
     Вик
    -0.05
    ：「
    -0.05
    POSITIVE LOGITS
    security
    0.07
     walks
    0.07
    ถาน
    0.07
    (TABLE
    0.06
    он
    0.06
     beş
    0.06
    actively
    0.06
    olution
    0.06
    <Map
    0.06
     rég
    0.06
    Act Density 0.041%

    No Known Activations