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

    Neuronpedia

    INDEX
    Explanations

    information processing or computation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    अप्र
    0.41
     लिं
    0.41
     CLEAN
    0.40
    BCD
    0.39
    டித்து
    0.39
     القناه
    0.39
    達成
    0.37
    逈
    0.37
    راحی
    0.37
    絴
    0.37
    POSITIVE LOGITS
     brain
    0.57
     мозга
    0.54
     CPU
    0.54
    CPU
    0.51
    brain
    0.50
    cpu
    0.49
     моз
    0.49
    Cpu
    0.48
    Brain
    0.48
     cerveau
    0.48
    Act Density 0.041%

    No Known Activations