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

    Neuronpedia

    INDEX
    Explanations

    stereotypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    0.80
    নি
    0.80
    Announcement
    0.74
     Restriction
    0.73
    خ
    0.71
     Ти
    0.70
     Три
    0.70
     популяр
    0.69
    ם
    0.69
     DEFAULT
    0.68
    POSITIVE LOGITS
     salas
    0.99
     verdes
    0.97
     señalar
    0.95
    arnia
    0.94
     vínculos
    0.94
    atii
    0.91
    leşt
    0.89
     taim
    0.89
     máquinas
    0.89
     lanza
    0.89
    Act Density 0.003%

    No Known Activations