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

    Neuronpedia

    INDEX
    Explanations

    important considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Suggested
    0.93
    Suggested
    0.91
     SUG
    0.89
     সাজেশন
    0.89
     suggest
    0.88
     Suggest
    0.83
     suggestion
    0.80
     Tipps
    0.79
     Suggestions
    0.79
     conclure
    0.78
    POSITIVE LOGITS
    もので
    0.88
    注意的是
    0.80
    重要的是
    0.78
    '*
    0.74
    ものです
    0.73
    ものである
    0.73
     olmadığını
    0.72
    oma
    0.71
     tersebut
    0.70
     sepenuhnya
    0.70
    Act Density 0.179%

    No Known Activations