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

    Neuronpedia

    INDEX
    Explanations

    keen to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ीय
    3.18
    ূলক
    2.99
    ास
    2.90
    cobra
    2.89
    𝐢
    2.89
    ἱ
    2.80
     sapply
    2.79
    ar
    2.77
     दर्ज
    2.74
    ک
    2.68
    POSITIVE LOGITS
    д
    2.83
    ства
    2.73
     увагу
    2.69
    н
    2.67
    м
    2.66
     insights
    2.63
    জনের
    2.61
    ندگان
    2.55
     llegado
    2.51
     ina
    2.36
    Act Density 0.009%

    No Known Activations