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

    Neuronpedia

    INDEX
    Explanations

    forum excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     公
    -0.07
     consciously
    -0.06
     cartridge
    -0.06
    Lady
    -0.06
    HEET
    -0.06
    HANDLE
    -0.06
     которым
    -0.06
    魔
    -0.06
     лок
    -0.06
    ':
    -0.06
    POSITIVE LOGITS
     clf
    0.07
     Chern
    0.07
    fight
    0.06
    ("-");↵
    0.06
     км
    0.06
    Dick
    0.06
    omnia
    0.06
     Unlock
    0.06
    verts
    0.06
     XCTestCase
    0.06
    Act Density 0.025%

    No Known Activations