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

    Neuronpedia

    INDEX
    Explanations

    inquiring about specific operational context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    學者
    0.43
     malattie
    0.43
     fabriqu
    0.42
     захворю
    0.41
     ní
    0.41
    ვნ
    0.40
     erreurs
    0.40
     dl
    0.39
    Jeśli
    0.39
     perdita
    0.38
    POSITIVE LOGITS
     operational
    0.46
     hoạt
    0.46
    operational
    0.44
     गतिविधियों
    0.41
    activities
    0.40
    thisComponent
    0.40
     activities
    0.39
    '.
    0.39
     نش
    0.39
     آن‌ها
    0.39
    Act Density 0.024%

    No Known Activations