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

    Neuronpedia

    INDEX
    Explanations

    markup and data formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ídio
    0.48
    é
    0.47
     leopard
    0.46
     pathophys
    0.46
     mindless
    0.46
     вулкан
    0.46
    öl
    0.46
     magma
    0.46
     médecine
    0.46
     मनोवैज्ञानिक
    0.46
    POSITIVE LOGITS
    xml
    0.76
     XML
    0.70
     xml
    0.69
     Xml
    0.57
    ुष
    0.54
    XML
    0.54
    രിയാ
    0.52
    ном
    0.51
    ფორმა
    0.51
    று
    0.49
    Act Density 0.661%

    No Known Activations