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

    Neuronpedia

    INDEX
    Explanations

    ancestral origins and lineage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    1.56
    }
    1.27
    ين
    1.16
    ра
    1.13
     instala
    1.07
    ]
    1.06
    {
    1.04
    ના
    1.00
    ють
    1.00
    لي
    0.98
    POSITIVE LOGITS
    า
    1.12
    ை
    1.05
    ಿಕ
    1.04
    3
    1.01
    baiki
    0.97
    EV
    0.91
    p
    0.90
    یک
    0.89
    می
    0.88
    ON
    0.87
    Act Density 0.003%

    No Known Activations