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

    Neuronpedia

    INDEX
    Explanations

    refrain, seat, chemin, soy, massage, mine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    0.52
    miR
    0.47
     नवरा
    0.46
    стве
    0.46
    ფორ
    0.44
     भला
    0.44
    кана
    0.44
     completed
    0.43
    ত্তম
    0.43
     Maulana
    0.43
    POSITIVE LOGITS
    ;";
    0.45
     personalità
    0.45
     উঠিয়া
    0.43
    elite
    0.43
     hipótesis
    0.43
     الأح
    0.42
     وګ
    0.42
    躲
    0.42
    仪
    0.42
    padding
    0.41
    Act Density 0.000%

    No Known Activations