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

    Neuronpedia

    INDEX
    Explanations

    natural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    求助
    -0.08
     excess
    -0.08
    纷
    -0.08
    微信
    -0.07
     kwargs
    -0.07
     Spencer
    -0.07
     Coins
    -0.07
     spreads
    -0.07
     Op
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     natural
    0.10
    lease
    0.08
     Nat
    0.07
    生物
    0.07
     длительн
    0.07
     CLR
    0.07
    rador
    0.07
     />,↵
    0.07
    ,
    0.07
    Natural
    0.07
    Act Density 0.028%

    No Known Activations