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

    Neuronpedia

    INDEX
    Explanations

    decisions related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Advert
    0.35
    CIT
    0.34
    hull
    0.34
     लगेंगे
    0.33
    Oval
    0.32
    Leadership
    0.32
    負責
    0.32
    Hull
    0.32
    มั่น
    0.32
    閔
    0.32
    POSITIVE LOGITS
     ​​
    0.35
     మాత్రమే
    0.35
    的一些
    0.34
    zęd
    0.33
     only
    0.33
     vragen
    0.32
     **)
    0.32
    ólnie
    0.32
    awcy
    0.32
     о
    0.31
    Act Density 0.011%

    No Known Activations