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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frag
    -0.07
     WD
    -0.07
    HasBeenSet
    -0.07
     priest
    -0.06
    ูร
    -0.06
     highest
    -0.06
     Lease
    -0.06
    [next
    -0.06
    387
    -0.06
     законом
    -0.06
    POSITIVE LOGITS
     ابزار
    0.07
    .VK
    0.07
     possessing
    0.06
    tiles
    0.06
    .SendMessage
    0.06
    /use
    0.06
     pave
    0.06
    .iso
    0.06
     aides
    0.06
     guides
    0.06
    Act Density 0.008%

    No Known Activations