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

    Neuronpedia

    INDEX
    Explanations

    getting started

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     próximas
    -0.09
    退出
    -0.08
    .Pe
    -0.08
     cellspacing
    -0.08
     atë
    -0.08
     ശേഷം
    -0.08
    കോ
    -0.08
     Employ
    -0.08
     ഹൈ
    -0.08
     படம்
    -0.08
    POSITIVE LOGITS
     gathered
    0.08
     duty
    0.08
     mats
    0.07
     legisl
    0.07
     gather
    0.07
     gel
    0.07
     drafted
    0.07
    アル
    0.07
    Mate
    0.07
    дум
    0.07
    Act Density 0.011%

    No Known Activations