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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Orden
    -0.08
     Darth
    -0.06
     All
    -0.06
    вичай
    -0.06
    ercul
    -0.06
    =is
    -0.06
    兹
    -0.06
     row
    -0.06
    ूम
    -0.06
    lüğü
    -0.06
    POSITIVE LOGITS
    egie
    0.07
    тів
    0.06
    .times
    0.06
    추천
    0.06
    digest
    0.06
    ۀ
    0.06
     CPU
    0.06
    Grant
    0.06
     ApplicationUser
    0.06
     Mack
    0.06
    Act Density 0.043%

    No Known Activations