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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =↵↵
    -0.07
     Ba
    -0.06
     responding
    -0.06
    Ba
    -0.06
     ba
    -0.06
     desp
    -0.06
     sóng
    -0.06
     Мет
    -0.06
    uers
    -0.06
    bett
    -0.06
    POSITIVE LOGITS
     annual
    0.07
     인천
    0.06
    .bar
    0.06
    378
    0.06
    (widget
    0.06
     Annual
    0.06
     season
    0.06
    ковой
    0.06
    uddled
    0.06
    фра
    0.06
    Act Density 0.022%

    No Known Activations