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

    Neuronpedia

    INDEX
    Explanations

    full

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perfeitamente
    -0.09
     perfectly
    -0.08
    进行了
    -0.08
    Chart
    -0.08
     Chart
    -0.08
     Perfect
    -0.08
    -chart
    -0.08
     ???↵↵
    -0.08
    ???↵↵
    -0.08
    .chart
    -0.07
    POSITIVE LOGITS
    不要
    0.14
     preferably
    0.13
     helst
    0.13
    ுங்கள்
    0.12
    至少
    0.11
    하세요
    0.11
     yourself
    0.11
     रखें
    0.11
     wisely
    0.11
    勿
    0.11
    Act Density 0.370%

    No Known Activations