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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .thumbnail
    -0.07
     росій
    -0.06
    ('[
    -0.06
     userList
    -0.06
    군요
    -0.06
    .tipo
    -0.06
     тепер
    -0.06
    -entry
    -0.06
     Už
    -0.06
    David
    -0.06
    POSITIVE LOGITS
    pling
    0.07
     bottled
    0.07
    ảng
    0.07
     mountain
    0.07
     constrain
    0.06
    nox
    0.06
     end
    0.06
     conf
    0.06
    _through
    0.06
     Honey
    0.06
    Act Density 0.001%

    No Known Activations