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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /render
    -0.08
     Seat
    -0.07
    Times
    -0.07
     Böylece
    -0.07
     MASK
    -0.06
     corn
    -0.06
     standards
    -0.06
     bott
    -0.06
    .Settings
    -0.06
     BOTTOM
    -0.06
    POSITIVE LOGITS
    日本
    0.06
    зм
    0.06
    -not
    0.06
     dissertation
    0.06
    ωτερ
    0.06
     Dissertation
    0.06
     ");
↵
    0.06
    _human
    0.06
     정도
    0.06
     nhiêu
    0.06
    Act Density 0.003%

    No Known Activations