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

    Neuronpedia

    INDEX
    Explanations

    Korean particles/endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    εις
    -0.07
     Mathematical
    -0.06
    mesine
    -0.06
     діяльність
    -0.06
     pointed
    -0.06
     cooling
    -0.06
     readily
    -0.06
     deleted
    -0.06
    ,'
    -0.06
     motivations
    -0.06
    POSITIVE LOGITS
    하여
    0.25
    해서
    0.16
    되어
    0.09
     ederek
    0.08
    어서
    0.08
    enido
    0.07
     Hoover
    0.07
     통해
    0.07
     Lon
    0.07
    аторы
    0.07
    Act Density 0.003%

    No Known Activations