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

    Neuronpedia

    INDEX
    Explanations

    existence or availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ấy
    0.37
    গুলিকে
    0.37
    ﺢ
    0.36
    fulness
    0.36
    一张
    0.35
    ilee
    0.35
     itself
    0.35
    Pa
    0.34
     نفسي
    0.34
    ﻲ
    0.34
    POSITIVE LOGITS
     ਜੋ
    0.54
     જેમાં
    0.52
     whereby
    0.51
     जिसमें
    0.51
     যেগুলো
    0.50
     wherein
    0.49
     जो
    0.47
     ज्यात
    0.46
     जिनमें
    0.46
     ដែល
    0.44
    Act Density 0.022%

    No Known Activations