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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and appreciation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appreciable
    1.10
    ேஷ்
    0.98
    €“
    0.98
     അവസ്ഥ
    0.97
     синх
    0.94
     resizing
    0.94
     apnea
    0.92
    SYNC
    0.90
     المعادلات
    0.90
    sync
    0.90
    POSITIVE LOGITS
     loudly
    0.94
    тельные
    0.88
     kèm
    0.85
    Complex
    0.81
    力度
    0.77
    মূলক
    0.77
     বাণী
    0.77
    ઠવા
    0.76
     glance
    0.76
    Alc
    0.76
    Act Density 0.216%

    No Known Activations