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

    Neuronpedia

    INDEX
    Explanations

    loaded libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perpetuity
    0.92
    т
    0.90
    気が
    0.84
    ଭ
    0.84
     breathless
    0.79
    드립니다
    0.78
     comorbid
    0.77
    ліза
    0.77
    ਾਮ
    0.77
     goutte
    0.75
    POSITIVE LOGITS
    的
    1.00
     является
    0.98
     الأ
    0.95
     это
    0.90
     víz
    0.90
    లో
    0.88
     двух
    0.88
    seits
    0.88
     Cómo
    0.88
     выше
    0.87
    Act Density 0.000%

    No Known Activations