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

    Neuronpedia

    INDEX
    Explanations

    false or migrated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pt
    0.41
     customised
    0.41
    moved
    0.41
    স্থিত
    0.41
     here
    0.41
    cl
    0.41
    of
    0.41
    ar
    0.40
     burada
    0.40
     plumbing
    0.40
    POSITIVE LOGITS
    ческие
    0.48
     위해
    0.44
    কে
    0.41
     reluct
    0.40
     Ire
    0.39
    해야
    0.38
    값이
    0.38
    柞
    0.38
    淖
    0.38
    arlama
    0.38
    Act Density 0.003%

    No Known Activations