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

    Neuronpedia

    INDEX
    Explanations

    development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     максим
    -0.07
    \-
    -0.07
     implication
    -0.07
    (Max
    -0.07
    ”
    -0.07
    -max
    -0.07
    Maximum
    -0.07
    efore
    -0.07
     maximale
    -0.07
    ¾
    -0.07
    POSITIVE LOGITS
    ാഷ്ട്ര
    0.09
    ാഷ്ട
    0.09
    klart
    0.08
    ේශ
    0.08
     KU
    0.08
    عديد
    0.08
     ropa
    0.08
    ovski
    0.08
     ചരിത്ര
    0.08
     shumë
    0.07
    Act Density 0.005%

    No Known Activations