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

    Neuronpedia

    INDEX
    Explanations

    ka ku ji wa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝟘
    0.47
    ००
    0.46
     Maverick
    0.45
     ساين
    0.44
     ஏற்க
    0.44
    ार्ट
    0.43
     العلاقات
    0.43
    ادس
    0.43
     क्रिकेटर
    0.43
    ОВ
    0.42
    POSITIVE LOGITS
    ka
    0.68
     k
    0.68
     ka
    0.65
    ku
    0.65
    ji
    0.64
    wa
    0.64
     ku
    0.61
     kako
    0.60
    ja
    0.58
    aka
    0.57
    Act Density 0.035%

    No Known Activations