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

    Neuronpedia

    INDEX
    Explanations

    Sanskrit language and Vedic texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     admires
    0.90
     jute
    0.81
     behold
    0.80
     Medved
    0.80
     말미암
    0.78
     whatnot
    0.78
    killers
    0.78
    iences
    0.78
     vyl
    0.77
     chaper
    0.77
    POSITIVE LOGITS
    로
    0.90
    În
    0.83
    ও
    0.82
    ik
    0.82
    usepackage
    0.77
    zh
    0.77
    ทางการ
    0.76
    ṃ
    0.75
    時点で
    0.75
    మంది
    0.74
    Act Density 0.028%

    No Known Activations