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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மேம்ப
    0.58
     komple
    0.46
    ناها
    0.46
     bekl
    0.45
    conder
    0.45
     pikir
    0.45
     kompleks
    0.45
     mengembangkan
    0.44
     शक्ती
    0.44
     zespół
    0.44
    POSITIVE LOGITS
    0
    0.70
    9
    0.66
    8
    0.66
    7
    0.66
    6
    0.61
    5
    0.56
    4
    0.55
    1
    0.54
    3
    0.51
    ab
    0.49
    Act Density 0.143%

    No Known Activations