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

    Neuronpedia

    INDEX
    Explanations

    URLs and specific descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    M
    0.51
    و
    0.45
    у
    0.44
    Alfred
    0.44
    F
    0.44
    W
    0.43
     sights
    0.42
    Dress
    0.41
    L
    0.41
    Ak
    0.41
    POSITIVE LOGITS
    ंश
    0.51
     tumhe
    0.48
    ্রাজ
    0.47
     BLUENRG
    0.47
     अनो
    0.47
     exame
    0.47
     ujian
    0.46
     sınav
    0.46
     semelhante
    0.46
     छापेमारी
    0.45
    Act Density 0.000%

    No Known Activations