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

    Neuronpedia

    INDEX
    Explanations

    Slavic names and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     днем
    -0.09
    Kinds
    -0.08
     vanligt
    -0.08
     сверху
    -0.08
    ación
    -0.08
    ificando
    -0.08
     받은
    -0.08
     закреп
    -0.07
     dioxide
    -0.07
     완료
    -0.07
    POSITIVE LOGITS
     (?,
    0.08
     اس
    0.08
     Hirsch
    0.08
    uvos
    0.08
    nga
    0.07
     Thierry
    0.07
     Isa
    0.07
     Howell
    0.07
     David
    0.07
    Michel
    0.07
    Act Density 0.017%

    No Known Activations