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

    Neuronpedia

    INDEX
    Explanations

    Buffer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.92
    ट
    0.91
     начи
    0.89
    Arsenal
    0.87
    0.86
    Hollywood
    0.85
    ieson
    0.84
    0.83
    Moscow
    0.81
    0.81
    POSITIVE LOGITS
     लिहाजा
    1.18
     rejuven
    1.15
    চূ
    1.14
     gew
    1.13
     juht
    1.11
    ศี
    1.11
    sächlich
    1.10
     oreille
    1.10
     aguas
    1.09
    বৎ
    1.09
    Act Density 0.001%

    No Known Activations