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

    Neuronpedia

    INDEX
    Explanations

    Excel formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amalg
    -0.08
     Brasil
    -0.08
     hydro
    -0.07
     ভিত্ত
    -0.07
     Kei
    -0.07
     Bertrand
    -0.07
    -less
    -0.07
    .Br
    -0.07
     zalo
    -0.07
    Based
    -0.07
    POSITIVE LOGITS
    范围
    0.10
     plage
    0.10
     диапаз
    0.10
     phạm
    0.10
    数组
    0.10
     نطاق
    0.09
     range
    0.09
     배열
    0.09
     iterable
    0.08
    иски
    0.08
    Act Density 0.005%

    No Known Activations