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

    Neuronpedia

    INDEX
    Explanations

    comma then descriptive word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сути
    0.44
     Hồ
    0.42
     değil
    0.41
    鲅
    0.41
     V
    0.40
     Ga
    0.40
     Logic
    0.39
     ла
    0.39
    В
    0.39
     ವೇ
    0.39
    POSITIVE LOGITS
     \,,
    0.39
     canisters
    0.39
    ्यूस
    0.36
     determinadas
    0.36
     ।”
    0.35
     (“
    0.35
     Anschließend
    0.35
     `>=`,
    0.35
    amsmath
    0.34
    ，”
    0.34
    Act Density 0.001%

    No Known Activations