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

    Neuronpedia

    INDEX
    Explanations

    learn about how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لأ
    0.49
     நோக்கி
    0.47
     പിന്നീ
    0.46
     ذہن
    0.45
     తగ్గి
    0.45
     হাব
    0.44
    URATION
    0.44
     ഉട
    0.44
     እስከ
    0.43
     целью
    0.43
    POSITIVE LOGITS
     about
    0.95
     how
    0.85
     tentang
    0.71
     hvordan
    0.66
    about
    0.64
    how
    0.64
     अबाउट
    0.64
     bagaimana
    0.63
     apie
    0.62
     về
    0.59
    Act Density 0.106%

    No Known Activations