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

    Neuronpedia

    INDEX
    Explanations

    attention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tz
    -0.08
     Reliable
    -0.07
    &type
    -0.06
    .assertNot
    -0.06
    known
    -0.06
     inflammation
    -0.06
     шляхом
    -0.06
    bable
    -0.06
    .mods
    -0.06
    čné
    -0.06
    POSITIVE LOGITS
     framing
    0.07
    Ì
    0.07
        ↵    ↵    ↵    ↵
    0.06
     منت
    0.06
     Government
    0.06
    _pulse
    0.06
    erras
    0.06
    分
    0.06
     ROUND
    0.06
     meaningless
    0.06
    Act Density 0.036%

    No Known Activations