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

    Neuronpedia

    INDEX
    Explanations

    Australian states and cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समझना
    0.60
    ima
    0.59
    Gulf
    0.59
    se
    0.56
    OB
    0.55
    B
    0.55
    ya
    0.54
     Gulf
    0.53
    s
    0.53
     i
    0.52
    POSITIVE LOGITS
    ла
    0.68
     utilidad
    0.64
     sockets
    0.63
    "
    0.60
    ле
    0.57
    লা
    0.55
    ্ড
    0.55
    "</
    0.55
     Policía
    0.54
    казыва
    0.52
    Act Density 0.000%

    No Known Activations