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

    Neuronpedia

    INDEX
    Explanations

    too + qualifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ায়ন
    0.38
     utilisant
    0.38
     membut
    0.38
     திரும்பி
    0.38
    3
    0.37
     vive
    0.37
    但不
    0.37
     yath
    0.36
     benar
    0.36
    antikan
    0.36
    POSITIVE LOGITS
     too
    1.09
     Too
    1.05
     слишком
    1.00
     TOO
    1.00
     terlalu
    0.98
    too
    0.91
    Too
    0.91
    太
    0.91
     demasiado
    0.90
     troppo
    0.85
    Act Density 0.098%

    No Known Activations