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

    Neuronpedia

    INDEX
    Explanations

    sentence endings and markdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gamanam
    0.37
    0.35
    了一個
    0.34
    الش
    0.34
    𝙜
    0.33
     লইয়
    0.33
    ানন্দ
    0.33
     ayatan
    0.32
     elastomers
    0.32
     گرفته
    0.32
    POSITIVE LOGITS
    そのため
    0.57
    特に
    0.50
    また
    0.48
    しかし
    0.47
     특히
    0.47
    例えば
    0.44
    특히
    0.43
     또한
    0.43
     단순히
    0.43
    その
    0.42
    Act Density 0.007%

    No Known Activations