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

    Neuronpedia

    INDEX
    Explanations

    pillars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     élargies
    0.46
     nặng
    0.41
    圈
    0.40
     ción
    0.40
    敢
    0.39
    тера
    0.39
    聊
    0.39
    <0xD5>
    0.38
    潤
    0.38
    چر
    0.38
    POSITIVE LOGITS
     pillars
    1.23
     pillar
    1.21
     Pillars
    1.13
     Pillar
    1.10
    pillars
    1.03
    pillar
    0.96
     pil
    0.82
    柱
    0.78
     Pilar
    0.71
     piers
    0.68
    Act Density 0.004%

    No Known Activations