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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     systematically
    -0.07
    基督徒
    -0.07
     servants
    -0.07
     TInt
    -0.07
    arrison
    -0.07
    坒
    -0.07
    ارة
    -0.07
     youths
    -0.07
    ération
    -0.07
     결국
    -0.07
    POSITIVE LOGITS
    legend
    0.09
    Gradient
    0.08
     Grab
    0.07
    .Debug
    0.07
    moment
    0.07
    (second
    0.07
    Minute
    0.07
    AMPLE
    0.07
     Register
    0.07
    -cookie
    0.07
    Act Density 0.090%

    No Known Activations