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

    Neuronpedia

    INDEX
    Explanations

    quarterly or numpy-stl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     त्या
    0.45
    Unity
    0.45
     clueless
    0.45
    Kode
    0.45
     ফেলে
    0.44
    つ
    0.44
     jeopard
    0.44
    ResourceType
    0.43
    Ди
    0.43
    Мо
    0.42
    POSITIVE LOGITS
     পৌর
    0.53
    sla
    0.52
     车
    0.47
    ىڭ
    0.46
    力和
    0.45
    阶
    0.45
    lá
    0.45
    ట్టిన
    0.44
    َالَ
    0.44
    ヨタ
    0.43
    Act Density 0.003%

    No Known Activations