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

    Neuronpedia

    INDEX
    Explanations

    Nobel Prize and awards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     squeezing
    0.48
     صارفین
    0.46
     configuring
    0.46
     hardcore
    0.45
     mou
    0.45
     kyll
    0.44
     ruining
    0.44
     drizz
    0.43
     clogging
    0.43
     unloading
    0.42
    POSITIVE LOGITS
     Award
    0.94
     Prize
    0.93
     prizes
    0.93
     Prizes
    0.92
    奖
    0.92
     prize
    0.90
    獎
    0.89
     awards
    0.86
     fellowships
    0.85
     décerné
    0.85
    Act Density 0.018%

    No Known Activations