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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     its
    1.93
    Its
    1.72
     Its
    1.71
    它的
    1.67
    its
    1.56
     jego
    1.51
     itself
    1.48
     которое
    1.33
     jeho
    1.27
     njegov
    1.23
    POSITIVE LOGITS
     themselves
    2.72
    Their
    2.27
     Their
    2.22
    their
    2.12
     their
    2.08
    mselves
    1.94
     leur
    1.92
     deres
    1.91
     leurs
    1.90
    他们的
    1.84
    Act Density 0.132%

    No Known Activations