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

    Neuronpedia

    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     {
↵
    -0.07
     Boxes
    -0.06
     eş
    -0.06
     labelled
    -0.06
     مشهد
    -0.06
     GM
    -0.05
     %.
    -0.05
    Ev
    -0.05
     Girlfriend
    -0.05
    �
    -0.05
    POSITIVE LOGITS
     thereof
    0.11
    -resistant
    0.08
    OF
    0.08
     newList
    0.07
     इसम
    0.07
     реп
    0.07
    roof
    0.07
    ريكي
    0.07
    nesení
    0.07
     coconut
    0.07
    Act Density 0.005%

    No Known Activations