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

    Neuronpedia

    INDEX
    Explanations

    each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     하겠습니다
    0.35
    的关键
    0.34
     இறுதியில்
    0.33
    watermelon
    0.32
    της
    0.32
    गराज
    0.32
    蟋
    0.32
    市场上
    0.32
     अतीत
    0.32
     прекра
    0.31
    POSITIVE LOGITS
     each
    1.45
     mỗi
    1.27
     varje
    1.23
     EACH
    1.23
     каждого
    1.17
    each
    1.16
     प्रत्येक
    1.16
     Each
    1.16
     каждом
    1.16
     каждой
    1.13
    Act Density 0.203%

    No Known Activations