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

    Neuronpedia

    INDEX
    Explanations

    ownership and possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.21
     iteratively
    0.19
     the
    0.19
     create
    0.19
    ic
    0.18
    aled
    0.18
    以
    0.18
     a
    0.18
    Using
    0.18
    简单
    0.17
    POSITIVE LOGITS
     own
    0.50
     próprios
    0.33
     propias
    0.33
     próprias
    0.33
     eigenen
    0.32
     OWN
    0.32
     propios
    0.31
     propres
    0.31
     włas
    0.31
     eigenes
    0.31
    Act Density 0.195%

    No Known Activations