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

    Neuronpedia

    INDEX
    Explanations

    programming data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    底
    -0.08
    contents
    -0.08
    撸
    -0.08
    lado
    -0.08
    ilim
    -0.07
     Matthew
    -0.07
    जो
    -0.07
    地下
    -0.07
    秦
    -0.07
    济
    -0.07
    POSITIVE LOGITS
     તારીખ
    0.10
     date
    0.10
     Date
    0.10
    OOLEAN
    0.09
    _boolean
    0.09
     boolean
    0.09
     날짜
    0.09
    Date
    0.09
     એવા
    0.09
    .date
    0.09
    Act Density 0.010%

    No Known Activations