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

    Neuronpedia

    INDEX
    Explanations

    tokenization strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     छव
    0.70
     parental
    0.68
    疼
    0.66
     Parental
    0.66
    ६
    0.64
    hanam
    0.63
    waves
    0.63
    .].
    0.63
     जिसका
    0.63
     waves
    0.62
    POSITIVE LOGITS
     NG
    0.70
     Nose
    0.70
     म्हणून
    0.68
     congel
    0.67
     modeller
    0.67
     Sumber
    0.66
     oss
    0.66
     फ्र
    0.66
     Fink
    0.66
     FRO
    0.66
    Act Density 0.000%

    No Known Activations