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

    Neuronpedia

    INDEX
    Explanations

    User feedback and advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     провед
    -0.07
     burst
    -0.07
    ucs
    -0.07
     irony
    -0.07
    isNew
    -0.07
    !";
↵
    -0.06
    DMA
    -0.06
     ISO
    -0.06
    �
    -0.06
     MyApp
    -0.06
    POSITIVE LOGITS
     coverage
    0.06
    逆
    0.06
     поля
    0.06
     VE
    0.06
     >&
    0.06
     ":"
    0.06
     sleepy
    0.06
     ";"
    0.05
     Soviets
    0.05
    105
    0.05
    Act Density 0.079%

    No Known Activations