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

    Neuronpedia

    INDEX
    Explanations

    requirements and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     realista
    1.02
     todo
    1.02
    zur
    1.01
    uré
    1.00
     usual
    0.97
     mọi
    0.96
    todo
    0.96
    classification
    0.95
     izra
    0.94
     apropri
    0.92
    POSITIVE LOGITS
     इन्हीं
    1.06
    женных
    0.99
     těchto
    0.99
     انہ
    0.95
     ইহার
    0.89
    ンの
    0.88
    ออกจาก
    0.88
     یہی
    0.87
    অম
    0.87
     공급
    0.86
    Act Density 0.499%

    No Known Activations