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

    Neuronpedia

    INDEX
    Explanations

    village description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    la
    1.14
    se
    1.09
    ن
    0.97
    ס
    0.95
     at
    0.95
    the
    0.95
     on
    0.92
     the
    0.85
     terminée
    0.85
     are
    0.85
    POSITIVE LOGITS
    1.20
    Village
    0.96
    村
    0.95
     villagers
    0.93
     I
    0.91
    村民
    0.89
    Е
    0.88
     làng
    0.85
     Village
    0.84
    "
    0.84
    Act Density 0.003%

    No Known Activations