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

    Neuronpedia

    INDEX
    Explanations

    tires and vehicle parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lunchtime
    -0.09
    abler
    -0.09
     dazu
    -0.08
    -ish
    -0.07
    日晚
    -0.07
    ности
    -0.07
    性生活
    -0.07
    edy
    -0.07
    ustada
    -0.07
     productive
    -0.07
    POSITIVE LOGITS
     geeignet
    0.10
     geschikt
    0.08
    you're
    0.08
     בעל
    0.08
     종류
    0.07
     commercially
    0.07
     milag
    0.07
     trimes
    0.07
    throw
    0.07
     selbst
    0.07
    Act Density 0.061%

    No Known Activations