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

    Neuronpedia

    INDEX
    Explanations

    castle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    391
    -0.07
     trio
    -0.07
    olumbia
    -0.07
    requencies
    -0.07
    iswa
    -0.07
     Iowa
    -0.07
     některých
    -0.07
    -worker
    -0.07
    (doc
    -0.06
     především
    -0.06
    POSITIVE LOGITS
     Castle
    0.18
     castle
    0.16
    Castle
    0.15
    城
    0.08
    па
    0.08
     palace
    0.08
     Palace
    0.08
     Abbey
    0.07
     Headquarters
    0.07
    lesh
    0.07
    Act Density 0.007%

    No Known Activations