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

    Neuronpedia

    INDEX
    Explanations

    score

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    洪
    -0.08
    Calibri
    -0.06
    RGB
    -0.06
     EditorGUI
    -0.06
     btn
    -0.06
    \Factories
    -0.06
    .Parameters
    -0.06
    дет
    -0.06
     �
    -0.06
    暮
    -0.06
    POSITIVE LOGITS
    ,”
    0.06
     kort
    0.06
     عوامل
    0.06
     відбу
    0.06
    金
    0.06
     вимог
    0.06
     перен
    0.06
     honest
    0.06
     dục
    0.06
     etkin
    0.06
    Act Density 0.014%

    No Known Activations