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

    Neuronpedia

    INDEX
    Explanations

    bandwidth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'action
    -0.07
    Emma
    -0.07
     automát
    -0.07
    837
    -0.07
    少し
    -0.07
    {}".
    -0.06
     Notes
    -0.06
    conn
    -0.06
    39
    -0.06
    'T
    -0.06
    POSITIVE LOGITS
     bandwidth
    0.15
     <!
    0.07
     Bran
    0.07
    !*
    0.07
    Speed
    0.06
    width
    0.06
    !!!!!
    0.06
    asking
    0.06
    .span
    0.06
     undis
    0.06
    Act Density 0.002%

    No Known Activations