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

    Neuronpedia

    INDEX
    Explanations

    happening at the same time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    阝
    0.37
    ጡ
    0.37
    ลักษณ์
    0.37
     мг
    0.36
    ጶ
    0.35
    风
    0.34
    不断
    0.34
    തിൽ
    0.34
    紆
    0.34
    ]^{
    0.33
    POSITIVE LOGITS
     coincides
    2.55
     coincided
    2.55
     coincide
    2.53
     coinciding
    2.41
     coincid
    2.05
     coinc
    1.99
     coincident
    1.96
     coincidence
    1.92
     совпада
    1.63
     сов
    1.40
    Act Density 0.006%

    No Known Activations