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

    Neuronpedia

    INDEX
    Explanations

    here are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ру
    1.07
    an
    1.07
    м
    1.03
    ز
    0.98
    દ
    0.97
     Roundup
    0.96
    ش
    0.94
    lı
    0.92
    दात
    0.92
     ventricle
    0.91
    POSITIVE LOGITS
    ۰۰
    1.15
    tedir
    1.11
    favourites
    1.09
    ০০
    1.05
    দিকে
    1.00
    ול
    1.00
    yum
    0.99
     trouvé
    0.99
    bonus
    0.99
     absolv
    0.98
    Act Density 0.294%

    No Known Activations