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

    Neuronpedia

    INDEX
    Explanations

    with programming objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sergei
    0.55
     ஆனால்
    0.55
     nhưng
    0.53
    тиви
    0.51
     اچھی
    0.50
    ikan
    0.50
    hbase
    0.50
     বিনিয়োগ
    0.49
     আয়নের
    0.49
     αλλά
    0.49
    POSITIVE LOGITS
    न
    0.58
    С
    0.55
    C
    0.54
    ⭐
    0.52
    ब
    0.51
    中文
    0.50
    $\
    0.49
    ↵↵
    0.48
     transm
    0.48
    D
    0.48
    Act Density 0.000%

    No Known Activations