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

    Neuronpedia

    INDEX
    Explanations

    museums, games, or specific places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.73
    ،
    0.63
    u
    0.59
    。
    0.56
    ప్
    0.53
    ig
    0.52
    ِ
    0.52
    at
    0.52
    ।
    0.52
    在
    0.52
    POSITIVE LOGITS
     calmness
    0.57
     teorías
    0.52
     शांत
    0.50
     reluctance
    0.49
     superfluous
    0.49
     stillness
    0.48
     aquellos
    0.48
     ceiling
    0.48
     esteem
    0.48
     treadmill
    0.48
    Act Density 0.000%

    No Known Activations