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

    Neuronpedia

    INDEX
    Explanations

    concise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    株
    0.46
    ဍ
    0.45
    の詳細
    0.45
     softening
    0.44
    ゆっくり
    0.44
     softness
    0.43
     devaluation
    0.43
    绵
    0.42
     گذشته
    0.42
    詳細
    0.41
    POSITIVE LOGITS
     summary
    0.62
     succinct
    0.61
     concise
    0.59
     brevity
    0.57
     gọn
    0.56
     concisely
    0.55
    summary
    0.55
     مختصر
    0.52
     succinctly
    0.52
     pith
    0.52
    Act Density 0.013%

    No Known Activations