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

    Neuronpedia

    INDEX
    Explanations

    готов

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruined
    -0.06
    	cnt
    -0.06
     Majesty
    -0.06
    関係
    -0.06
    れる
    -0.06
     questionable
    -0.06
    Memory
    -0.06
    notin
    -0.06
    िनक
    -0.06
     runners
    -0.06
    POSITIVE LOGITS
     plagiar
    0.07
    [port
    0.07
     fuss
    0.06
     вор
    0.06
    ensem
    0.06
     fils
    0.06
    .stat
    0.06
    (Value
    0.06
     destinations
    0.06
    โต
    0.06
    Act Density 0.007%

    No Known Activations