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

    Neuronpedia

    INDEX
    Explanations

    in this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಿಯಾ
    0.63
    inside
    0.62
     inside
    0.58
    Di
    0.57
    ジン
    0.56
     تلق
    0.55
     দিয়া
    0.54
    юр
    0.53
     داخل
    0.53
     move
    0.53
    POSITIVE LOGITS
     in
    1.83
     ใน
    1.81
    在本
    1.76
    在这种
    1.69
    ใน
    1.65
    今回は
    1.57
     în
    1.52
     данном
    1.50
     في
    1.50
    在这个
    1.45
    Act Density 0.385%

    No Known Activations