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

    Neuronpedia

    INDEX
    Explanations

    military ranks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asteroid
    -0.07
    Nu
    -0.07
     материал
    -0.07
    네요
    -0.07
     utilities
    -0.07
    Muon
    -0.06
    TreeView
    -0.06
     Ferry
    -0.06
    نسان
    -0.06
     artillery
    -0.06
    POSITIVE LOGITS
     départ
    0.06
    ា�
    0.06
     каф
    0.06
     Former
    0.06
     맡
    0.06
    	random
    0.06
    Directories
    0.06
     BRAND
    0.06
    мі
    0.06
     Drake
    0.06
    Act Density 0.006%

    No Known Activations