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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EPROM
    -0.06
     beste
    -0.06
    mmc
    -0.06
     ок
    -0.06
    WithEmail
    -0.06
    ریان
    -0.06
     dhcp
    -0.05
    LOC
    -0.05
     doğrudan
    -0.05
    filtr
    -0.05
    POSITIVE LOGITS
     quotas
    0.07
     Presentation
    0.07
     contest
    0.06
     Papers
    0.06
     them
    0.06
     �
    0.06
     inne
    0.06
     Mits
    0.06
     nothing
    0.06
    case
    0.06
    Act Density 0.006%

    No Known Activations