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

    Neuronpedia

    INDEX
    Explanations

    hot air balloons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Isra
    0.54
    জাম
    0.53
    RNN
    0.53
     çık
    0.52
    Rama
    0.51
     Hương
    0.49
     aplik
    0.48
    Наша
    0.47
     вирі
    0.47
    MATH
    0.47
    POSITIVE LOGITS
     โดย
    0.60
    旁
    0.58
    etaan
    0.56
    年
    0.55
    ពួកគេ
    0.53
     ඔවුන්
    0.53
     있는데
    0.52
     ისინი
    0.52
     है
    0.52
    ர்கள்
    0.51
    Act Density 0.002%

    No Known Activations