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

    Neuronpedia

    INDEX
    Explanations

    offer more details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     üzerine
    0.92
     yêu
    0.90
    गित
    0.87
    iennes
    0.86
     занима
    0.86
    orada
    0.83
    нове
    0.83
    érables
    0.83
    மாய
    0.82
    upon
    0.81
    POSITIVE LOGITS
     fasi
    1.06
     okol
    1.00
     pelo
    0.97
     questa
    0.97
     any
    0.95
     qualquer
    0.93
     multe
    0.91
     cette
    0.88
     surrounding
    0.88
    relse
    0.88
    Act Density 0.015%

    No Known Activations