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

    Neuronpedia

    INDEX
    Explanations

    high

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kingdom
    -0.07
    ，以
    -0.07
    OL
    -0.07
    以
    -0.06
     constitutional
    -0.06
    ุก
    -0.06
    .room
    -0.06
     sockfd
    -0.06
     فيها
    -0.06
    <Component
    -0.06
    POSITIVE LOGITS
    +'.
    0.07
    coc
    0.07
    طلق
    0.06
    Transactions
    0.06
    ouver
    0.06
    udder
    0.06
    }.
    0.06
    IBUTES
    0.06
     Panc
    0.06
     سام
    0.06
    Act Density 0.048%

    No Known Activations