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

    Neuronpedia

    INDEX
    Explanations

    Tell

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।-
    0.83
    -【
    0.78
     fours
    0.74
    LayoutStyle
    0.71
    ابقة
    0.69
     equipment
    0.69
     diese
    0.69
     نست
    0.67
    equipment
    0.67
     arquitet
    0.67
    POSITIVE LOGITS
     me
    1.16
     μου
    0.92
     them
    0.92
     আমাকে
    0.89
     her
    0.86
     us
    0.83
     мне
    0.81
    her
    0.75
     меня
    0.73
     ей
    0.73
    Act Density 0.021%

    No Known Activations