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

    Neuronpedia

    INDEX
    Explanations

    versions and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innebär
    0.45
     jaaye
    0.43
    กก
    0.41
    дор
    0.40
    јан
    0.40
     saddhim
    0.39
    ន្ត
    0.39
    maxim
    0.39
    ່າງ
    0.39
    ким
    0.38
    POSITIVE LOGITS
     America
    0.47
     The
    0.46
     more
    0.44
     Albert
    0.42
     SF
    0.42
     "
    0.42
     '
    0.42
     Who
    0.42
     SA
    0.42
     Philip
    0.42
    Act Density 0.000%

    No Known Activations