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

    Neuronpedia

    INDEX
    Explanations

    election to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ヽ
    0.70
     hinzuf
    0.68
    čio
    0.67
     ব্র্যান্ড
    0.67
    避け
    0.66
     পরীক্ষায়
    0.65
    ची
    0.64
    SizePolicy
    0.63
    ambda
    0.63
     ध
    0.62
    POSITIVE LOGITS
     used
    2.56
    used
    2.33
     Used
    2.32
    用于
    2.30
    Used
    2.18
    用来
    2.10
     USED
    2.07
     usados
    1.97
     用于
    1.92
     usado
    1.91
    Act Density 0.739%

    No Known Activations