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

    Neuronpedia

    INDEX
    Explanations

    users from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     berasal
    0.52
     provenant
    0.47
     vanuit
    0.46
     لتح
    0.45
    ogia
    0.44
     originating
    0.43
     originate
    0.40
     pochod
    0.40
     из
    0.39
     నె
    0.39
    POSITIVE LOGITS
     khỏi
    0.66
    免
    0.46
     adequately
    0.42
     shielding
    0.42
     adequ
    0.41
    จากการ
    0.41
     adegu
    0.40
    maktan
    0.40
     safe
    0.40
     impecc
    0.40
    Act Density 0.020%

    No Known Activations