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

    Neuronpedia

    INDEX
    Explanations

    first step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     finally
    1.10
     akhirnya
    1.08
    Finally
    1.08
     Finally
    1.03
     впервые
    1.00
     anderer
    0.99
    最终
    0.98
    finally
    0.98
     lastly
    0.96
    まずは
    0.94
    POSITIVE LOGITS
     few
    2.01
     steps
    1.51
     Few
    1.44
     stages
    1.44
     foray
    1.44
    few
    1.43
     দিকের
    1.27
    Few
    1.26
     ever
    1.25
     step
    1.22
    Act Density 0.203%

    No Known Activations