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

    Neuronpedia

    INDEX
    Explanations

    introducing names or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    महिलाओं
    0.92
    美国的
    0.92
     mulheres
    0.83
     utilizzare
    0.83
     popularly
    0.83
     البنات
    0.82
     lézards
    0.81
     petani
    0.81
     américains
    0.80
     niemie
    0.80
    POSITIVE LOGITS
     MM
    0.79
     X
    0.78
     M
    0.78
     Х
    0.77
     K
    0.77
     М
    0.76
     W
    0.73
     CC
    0.73
     L
    0.73
     Г
    0.72
    Act Density 0.223%

    No Known Activations