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

    Neuronpedia

    INDEX
    Explanations

    change increase decrease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وقتی
    0.44
    }')
    0.42
     när
    0.41
     bodo
    0.40
    Converters
    0.40
    halt
    0.39
     gdy
    0.39
     следующий
    0.39
     spielte
    0.39
     året
    0.39
    POSITIVE LOGITS
     технологий
    0.42
    病人
    0.42
    ПО
    0.42
     debemos
    0.41
    KAL
    0.41
     POUR
    0.40
    ких
    0.40
    니
    0.40
    פור
    0.39
    입니다
    0.39
    Act Density 0.001%

    No Known Activations