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

    Neuronpedia

    INDEX
    Explanations

    approximate mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    त्रेयी
    0.56
     指輪
    0.46
    0.46
     һәм
    0.45
    斋
    0.45
     periodistas
    0.45
     पाण्डेय
    0.44
    {\'
    0.44
    горе
    0.44
    监狱
    0.44
    POSITIVE LOGITS
     \#
    0.54
     wers
    0.49
    }^{\
    0.48
     tuvo
    0.47
     Gave
    0.45
     ALWAYS
    0.44
    ]$
    0.44
     stesse
    0.44
     KNOW
    0.43
     tuve
    0.43
    Act Density 0.005%

    No Known Activations