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

    Neuronpedia

    INDEX
    Explanations

    cost savings and cost-effectiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     swamps
    0.79
     graduated
    0.75
    ຂ
    0.72
     Specify
    0.68
     fines
    0.67
     Des
    0.67
    র্ণ
    0.66
     petitions
    0.66
     multist
    0.65
     kidding
    0.65
    POSITIVE LOGITS
    lier
    0.79
     elementów
    0.76
    roductive
    0.76
     hareket
    0.75
    liest
    0.75
     Element
    0.74
    مد
    0.74
     наверное
    0.74
     эффектив
    0.72
     elementy
    0.72
    Act Density 0.122%

    No Known Activations