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

    Neuronpedia

    INDEX
    Explanations

    key improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sec
    0.63
     Oral
    0.62
     SEC
    0.61
     Second
    0.61
    Sec
    0.60
     passé
    0.60
     sec
    0.59
    प्ला
    0.59
     Sauvignon
    0.59
    ATG
    0.59
    POSITIVE LOGITS
     যৌগ
    0.54
     مست
    0.54
    ଫ
    0.53
     mPreview
    0.53
    djang
    0.53
    moil
    0.53
     ferram
    0.52
     फु
    0.51
     mű
    0.51
     Aze
    0.51
    Act Density 0.209%

    No Known Activations