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

    Neuronpedia

    INDEX
    Explanations

    color names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بنا
    0.40
     typeface
    0.39
    Acceleration
    0.39
    字体
    0.38
     ман
    0.37
    出版社
    0.36
     lettera
    0.35
     Guz
    0.35
     trigon
    0.35
     పద
    0.35
    POSITIVE LOGITS
    lie
    0.45
     Dit
    0.45
     dit
    0.43
     Przy
    0.42
     Green
    0.42
     dito
    0.41
    liet
    0.39
    一来
    0.39
    green
    0.38
    vény
    0.38
    Act Density 0.001%

    No Known Activations