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

    Neuronpedia

    INDEX
    Explanations

    Aspir, Assume, measures, quality, tableView

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cumin
    0.46
     kring
    0.46
    CUSS
    0.44
    iniai
    0.43
    裹
    0.43
    マータイヤ
    0.42
    тей
    0.42
    रिस
    0.42
     COMMUN
    0.42
    య్య
    0.41
    POSITIVE LOGITS
     frantically
    0.45
    pline
    0.44
    otically
    0.44
    र्या
    0.44
    Shore
    0.44
    ﻴ
    0.44
     باشید
    0.43
     یونی
    0.43
     ईयर
    0.43
    זו
    0.43
    Act Density 0.000%

    No Known Activations