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

    Neuronpedia

    INDEX
    Explanations

    it they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    viz
    -0.06
    Both
    -0.06
    DAO
    -0.06
    Clusters
    -0.06
    Booking
    -0.06
    (av
    -0.06
    .bias
    -0.06
    .init
    -0.05
    meni
    -0.05
    .inverse
    -0.05
    POSITIVE LOGITS
     Ripple
    0.08
    ΕΥ
    0.07
    apeake
    0.07
    eb
    0.07
     благ
    0.07
    ohon
    0.07
     Eff
    0.07
    4
    0.06
    льт
    0.06
     praise
    0.06
    Act Density 0.063%

    No Known Activations