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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and ownership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eric
    0.69
    धक
    0.68
    onic
    0.65
    herent
    0.63
     சென்ற
    0.63
     Rücken
    0.62
    inschaft
    0.62
    汜
    0.61
     mogen
    0.61
     instructive
    0.60
    POSITIVE LOGITS
     свои
    1.16
     своя
    1.04
     свої
    0.96
     свою
    0.93
     свое
    0.90
     своих
    0.90
     своё
    0.89
     अपना
    0.85
    their
    0.84
     자신이
    0.83
    Act Density 0.140%

    No Known Activations