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

    Neuronpedia

    INDEX
    Explanations

    possessives referring to ownership or self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হইয়
    0.22
    дал
    0.22
    ürz
    0.22
    ホル
    0.22
    aspir
    0.22
    或其他
    0.21
    iu
    0.20
    asey
    0.20
    The
    0.20
    तौर
    0.20
    POSITIVE LOGITS
     own
    0.61
     eigenen
    0.48
     propios
    0.46
     propias
    0.46
     próprias
    0.46
     próprios
    0.44
     propres
    0.43
     eigenes
    0.42
     eigene
    0.40
     próprio
    0.40
    Act Density 0.124%

    No Known Activations