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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and personal attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.24
    a
    0.23
    with
    0.23
     =
    0.22
    an
    0.21
    ("
    0.21
     -
    0.19
    r
    0.19
    }
    0.19
     {
    0.18
    POSITIVE LOGITS
     own
    0.22
     intentions
    0.21
     instincts
    0.18
     predicament
    0.18
     motivations
    0.18
     preferências
    0.18
     personal
    0.18
     próprias
    0.18
     propias
    0.17
     temperament
    0.17
    Act Density 0.671%

    No Known Activations