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

    Neuronpedia

    INDEX
    Explanations

    washes away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     odnosno
    0.87
    atau
    0.84
    lumat
    0.82
    ‌.
    0.79
     (!)
    0.78
     অনুষ্ঠিত
    0.78
    😐
    0.77
    (!)
    0.77
    skiy
    0.75
     ossia
    0.75
    POSITIVE LOGITS
    不仅
    1.90
    不僅
    1.70
     both
    1.62
     BOTH
    1.58
    뿐
    1.55
    だけでなく
    1.53
     גם
    1.50
     både
    1.50
     nejen
    1.49
     also
    1.44
    Act Density 0.346%

    No Known Activations