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

    Neuronpedia

    INDEX
    Explanations

    data definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Summary
    0.68
     Tool
    0.68
    compre
    0.64
     بم
    0.64
    hexagon
    0.63
     Summary
    0.62
    Summit
    0.62
     Synopsis
    0.62
     Preferred
    0.62
     Company
    0.62
    POSITIVE LOGITS
     semuanya
    0.90
     berp
    0.81
     bagi
    0.78
     aku
    0.76
     setiap
    0.74
     forskjellige
    0.72
    给你
    0.72
     eres
    0.71
     przygot
    0.71
     keseluruhan
    0.71
    Act Density 0.088%

    No Known Activations