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

    Neuronpedia

    INDEX
    Explanations

    shop and its people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    1.03
    সহ
    0.94
     написа
    0.83
     is
    0.80
     свадь
    0.80
    ]
    0.79
    Descrição
    0.77
    consulta
    0.77
     lorsqu
    0.75
     rebate
    0.74
    POSITIVE LOGITS
    ية
    0.88
    ট
    0.87
    ন
    0.84
    いた
    0.81
     in
    0.80
    υ
    0.75
    ల
    0.75
    ટ
    0.75
    dale
    0.73
    ون
    0.72
    Act Density 0.002%

    No Known Activations