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

    Neuronpedia

    INDEX
    Explanations

    Title context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izes
    1.16
     olmayan
    1.13
     or
    1.12
     portions
    1.10
    ли
    1.03
    적인
    1.03
     lekker
    1.02
    特定の
    1.02
     identifiable
    1.00
    น
    1.00
    POSITIVE LOGITS
    )`;
    1.38
    |।
    1.27
     infección
    1.24
     trazendo
    1.22
    0
    1.22
    ]++;
    1.17
    ༔
    1.06
    ется
    1.05
    ของการ
    1.03
     пыта
    1.02
    Act Density 0.440%

    No Known Activations