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

    Neuronpedia

    INDEX
    Explanations

    Numbers in articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    คู่
    -0.09
     witches
    -0.07
    valuer
    -0.07
     monarch
    -0.07
     manual
    -0.07
     inflicted
    -0.07
     valuations
    -0.07
    λάχισ
    -0.07
     wart
    -0.07
     ordeal
    -0.07
    POSITIVE LOGITS
    年至
    0.08
    刊
    0.08
    posite
    0.08
     professors
    0.08
    Fetched
    0.08
    ucene
    0.07
     meta
    0.07
     академ
    0.07
    Neighbour
    0.07
    日报道
    0.07
    Act Density 0.013%

    No Known Activations