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

    Neuronpedia

    INDEX
    Explanations

    cliques and graph theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unday
    -0.10
     iyadoo
    -0.09
     indian
    -0.08
     ...↵
    -0.08
    .algorithm
    -0.08
     …↵
    -0.08
     hauled
    -0.08
     (...)
    -0.08
     лоз
    -0.08
     разум
    -0.08
    POSITIVE LOGITS
    -knit
    0.10
     surrounded
    0.09
     mutual
    0.08
    iance
    0.08
     membership
    0.08
     unanim
    0.08
     참석
    0.08
    unkt
    0.07
     enclosed
    0.07
     behandeld
    0.07
    Act Density 0.013%

    No Known Activations