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

    Neuronpedia

    INDEX
    Explanations

    decomposing, explaining, maximizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    प्पू
    0.46
     başlayan
    0.44
    ={'
    0.42
    গুণ
    0.42
    æk
    0.41
     پڑھ
    0.41
    python
    0.41
     organisational
    0.41
     başlat
    0.41
    💊
    0.41
    POSITIVE LOGITS
    本身的
    0.44
     solicitudes
    0.44
     Muy
    0.42
     jeden
    0.41
     제작
    0.41
     speculations
    0.41
     nacht
    0.41
     especial
    0.40
     Obr
    0.40
     खी
    0.40
    Act Density 0.007%

    No Known Activations