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

    Neuronpedia

    INDEX
    Explanations

    market competition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Donnell
    0.38
     packaged
    0.38
     काढ
    0.37
     trud
    0.37
     ditu
    0.35
     packet
    0.35
     Strom
    0.35
     legalization
    0.35
    ดำเนิน
    0.35
     Latter
    0.34
    POSITIVE LOGITS
    Prototype
    0.42
     सुने
    0.42
     архів
    0.41
     titanium
    0.41
    不明
    0.40
    rivit
    0.40
     Prototype
    0.40
    ర్ణ
    0.40
    塔
    0.40
     Psych
    0.39
    Act Density 0.002%

    No Known Activations