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

    Neuronpedia

    INDEX
    Explanations

    data were, reference error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     P
    1.07
     H
    1.03
     K
    1.01
     E
    1.01
     B
    0.91
     James
    0.91
     John
    0.90
     Peter
    0.90
     Anthony
    0.89
     Henry
    0.89
    POSITIVE LOGITS
     ofthe
    1.11
     ഓഫ്
    1.10
     दिवसीय
    1.04
    ;*/
    1.04
     ของ
    1.00
    Metrics
    1.00
    ből
    0.98
     podataka
    0.97
     galerinha
    0.97
    usuarios
    0.96
    Act Density 0.000%

    No Known Activations