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

    Neuronpedia

    INDEX
    Explanations

    simple, basic, low-cost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ফুল্ল
    0.47
     shorter
    0.46
    पू
    0.41
    SIAN
    0.39
     weakening
    0.39
    新能源
    0.39
    돔
    0.38
     popularity
    0.36
     FULL
    0.36
    IANS
    0.36
    POSITIVE LOGITS
     manually
    0.99
     simple
    0.95
    simple
    0.92
     semplici
    0.92
     homemade
    0.91
     handmade
    0.91
     semplice
    0.89
    シンプルな
    0.87
    简单的
    0.87
     makeshift
    0.86
    Act Density 0.023%

    No Known Activations