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

    Neuronpedia

    INDEX
    Explanations

    notes and sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     그래도
    0.50
     nevertheless
    0.48
     nonetheless
    0.45
    ই
    0.42
    也沒有
    0.41
    CTED
    0.41
    卻
    0.41
    還是
    0.40
     Dead
    0.39
    也没有
    0.39
    POSITIVE LOGITS
     eftersom
    0.52
     puisque
    0.48
     αφού
    0.45
     which
    0.44
     což
    0.44
     sebagai
    0.43
    Which
    0.42
     όπως
    0.42
     puisqu
    0.42
     поговори
    0.41
    Act Density 0.156%

    No Known Activations