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

    Neuronpedia

    INDEX
    Explanations

    pronoun and 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fueran
    1.11
    Skirt
    1.09
     olhar
    1.07
     parecer
    1.07
     সৎ
    1.07
     veía
    1.06
    िज
    1.05
     पिछले
    1.05
    誹
    1.04
     foncé
    1.04
    POSITIVE LOGITS
     обеспечи
    1.07
     edilmiş
    1.05
    panies
    1.02
    ri
    0.96
     subscript
    0.93
     Wellesley
    0.91
    leqslant
    0.89
    مین
    0.89
    щую
    0.88
     laine
    0.88
    Act Density 0.000%

    No Known Activations