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

    Neuronpedia

    INDEX
    Explanations

    computer hardware and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    停車
    0.89
     memulai
    0.88
     הראשון
    0.88
     Himself
    0.87
    に乗
    0.85
     Informatika
    0.84
    捧
    0.81
    <unused314>
    0.80
     باسم
    0.79
    不幸
    0.79
    POSITIVE LOGITS
    𝘀
    0.94
    tolerance
    0.88
    𝗸
    0.88
    يًا
    0.88
    тэй
    0.85
    𝗿
    0.84
    क
    0.84
    yra
    0.83
    ન
    0.83
    temps
    0.82
    Act Density 0.097%

    No Known Activations