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

    Neuronpedia

    INDEX
    Explanations

    making things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     congestion
    0.36
     noxious
    0.36
    しゃれ
    0.35
     replay
    0.35
    வுக்கு
    0.35
     cloves
    0.35
     ammonia
    0.34
     ज्‍यादा
    0.34
    ंटिक
    0.34
    ⢿
    0.34
    POSITIVE LOGITS
     thereof
    0.48
     сами
    0.42
     उसमे
    0.41
     therefrom
    0.41
     নিজেই
    0.40
     самих
    0.40
     MADE
    0.39
     melakukannya
    0.39
     그걸
    0.38
    それを
    0.38
    Act Density 0.217%

    No Known Activations