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

    Neuronpedia

    INDEX
    Explanations

    pretty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nate
    -0.07
    God
    -0.07
     atmospheric
    -0.07
    (end
    -0.06
     který
    -0.06
     недели
    -0.06
    Coroutine
    -0.06
     Ferm
    -0.06
     bump
    -0.06
    ительных
    -0.06
    POSITIVE LOGITS
    -email
    0.06
     preocup
    0.06
     وان
    0.06
    orem
    0.06
    cut
    0.06
     провод
    0.06
    attribute
    0.06
     concent
    0.06
     đột
    0.06
    .toDouble
    0.06
    Act Density 0.015%

    No Known Activations