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

    Neuronpedia

    INDEX
    Explanations

    tables or spreadsheets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     കാണ
    -0.09
    718
    -0.08
    Segue
    -0.08
    Sid
    -0.08
     ισ
    -0.08
     aangeven
    -0.08
    Concern
    -0.08
    Isi
    -0.08
    这种
    -0.08
    ually
    -0.08
    POSITIVE LOGITS
     miscellaneous
    0.10
     taxes
    0.09
    费用
    0.09
     logo
    0.08
    /month
    0.08
     licenses
    0.08
     расходы
    0.08
     phí
    0.08
     upfront
    0.08
     marketing
    0.08
    Act Density 0.015%

    No Known Activations