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

    Neuronpedia

    INDEX
    Explanations

    )arg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scorer
    -0.07
    化
    -0.06
     Adding
    -0.06
    PTION
    -0.06
    чить
    -0.06
    وست
    -0.06
    itions
    -0.06
    -R
    -0.06
    IMUM
    -0.06
     Renaissance
    -0.05
    POSITIVE LOGITS
     Roads
    0.07
    .contract
    0.07
    ่ละ
    0.07
    .createStatement
    0.06
     opposes
    0.06
     الشر
    0.06
    ,proto
    0.06
     سمت
    0.06
     consuming
    0.06
    pdev
    0.06
    Act Density 0.003%

    No Known Activations