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

    Neuronpedia

    INDEX
    Explanations

    adjective endings and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wetlands
    0.35
     sweets
    0.33
    ంచెం
    0.33
     nicknamed
    0.32
    ٹنے
    0.32
     isten
    0.32
     commits
    0.31
     abbreviated
    0.31
     Crypto
    0.31
     Autumn
    0.30
    POSITIVE LOGITS
    에서도
    0.38
    !:
    0.36
    หรือ
    0.35
    !).
    0.35
    вала
    0.35
    сі
    0.34
    ）。
    0.34
     ឬ
    0.34
    오
    0.33
     중에
    0.33
    Act Density 0.066%

    No Known Activations