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

    Neuronpedia

    INDEX
    Explanations

    my, meine, and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    独特的
    0.68
     уника
    0.65
    特定の
    0.65
     способны
    0.63
    ®.
    0.59
     चक्रवृद्धि
    0.59
     víctimas
    0.58
    トラブル
    0.58
    VIP
    0.58
    的一种
    0.58
    POSITIVE LOGITS
     meine
    0.91
     meiner
    0.89
     moje
    0.89
     my
    0.87
     minha
    0.86
     내가
    0.86
     मैंने
    0.85
     myself
    0.84
     mijn
    0.82
     minhas
    0.82
    Act Density 0.074%

    No Known Activations