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

    Neuronpedia

    INDEX
    Explanations

    aspect of this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अधीक्षक
    0.79
     ಕೆಲವು
    0.74
    Tipo
    0.73
    Gu
    0.73
    Smartphone
    0.72
    Quem
    0.71
    нити
    0.70
    мимо
    0.70
     acompaña
    0.70
    indelijk
    0.69
    POSITIVE LOGITS
     thereof
    1.04
     of
    1.03
     ofthe
    0.97
     hereof
    0.85
     thưởng
    0.78
     tử
    0.76
     puzzle
    0.75
     missed
    0.75
     quên
    0.74
    ridge
    0.74
    Act Density 0.112%

    No Known Activations