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

    Neuronpedia

    INDEX
    Explanations

    final step or conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Th
    0.85
    othi
    0.81
    /*
    0.79
     TH
    0.75
    Gr
    0.73
    Sk
    0.72
     অনুরাগ
    0.72
     Austausch
    0.72
    的信息
    0.71
     Th
    0.71
    POSITIVE LOGITS
     Finally
    0.85
     finally
    0.83
    Lastly
    0.78
     നടത്തി
    0.78
    finally
    0.77
     '':
    0.75
    Finally
    0.75
    蝮
    0.73
    ennan
    0.71
    Finalmente
    0.69
    Act Density 0.097%

    No Known Activations