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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     شدہ
    0.35
     dispositivi
    0.33
    笊
    0.33
     vaš
    0.33
     따른
    0.32
     ਵਾਲ
    0.32
    fNil
    0.32
     your
    0.32
     ਤੁਹਾ
    0.32
    henderit
    0.32
    POSITIVE LOGITS
    selves
    0.35
    self
    0.34
    sel
    0.34
     in
    0.33
    den
    0.33
    elt
    0.33
    с
    0.33
     own
    0.32
    selt
    0.32
     próprio
    0.32
    Act Density 0.003%

    No Known Activations