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

    Neuronpedia

    INDEX
    Explanations

    style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ceive
    -0.07
    邲
    -0.07
    rowing
    -0.07
    /graphql
    -0.07
     Such
    -0.06
    Effective
    -0.06
    𝘏
    -0.06
    超强
    -0.06
    系列
    -0.06
    展区
    -0.06
    POSITIVE LOGITS
    redirect
    0.07
     wand
    0.07
    随之
    0.06
     rock
    0.06
    太多
    0.06
    多年
    0.06
     Gradient
    0.06
    ít
    0.06
     casa
    0.06
    JUnit
    0.06
    Act Density 0.007%

    No Known Activations