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

    Neuronpedia

    INDEX
    Explanations

    divide and conquer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gobernador
    0.88
    цию
    0.87
     wynik
    0.86
     tomada
    0.85
     personalidade
    0.84
     началась
    0.82
     marcha
    0.82
     infancia
    0.80
     asumir
    0.80
    ﻛ
    0.79
    POSITIVE LOGITS
    Пі
    1.00
    ся
    0.89
    ছেন
    0.89
    り
    0.88
    ;');
    0.84
    дан
    0.83
    ́ng
    0.81
     Retreat
    0.80
     човек
    0.80
     cris
    0.79
    Act Density 0.000%

    No Known Activations