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

    Neuronpedia

    INDEX
    Explanations

    her or she

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entend
    0.98
     on
    0.97
     deres
    0.97
    تهای
    0.96
     encargado
    0.96
     avevano
    0.93
     sencillo
    0.92
     peligro
    0.92
     antiguo
    0.89
     attivo
    0.89
    POSITIVE LOGITS
     in
    1.77
    ،
    1.44
    ة
    1.39
    在
    1.29
     herself
    1.25
    in
    1.23
     في
    1.18
    ও
    1.16
    ，
    1.09
    s
    1.08
    Act Density 0.186%

    No Known Activations