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

    Neuronpedia

    INDEX
    Explanations

    Numbers in times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     durability
    -0.07
    Check
    -0.07
     uname
    -0.07
     vaccination
    -0.07
    Magento
    -0.06
     August
    -0.06
    еров
    -0.06
    (head
    -0.06
     seper
    -0.06
    742
    -0.06
    POSITIVE LOGITS
     enctype
    0.07
    uglify
    0.07
    .OneToOne
    0.07
     getOrder
    0.07
    .LEADING
    0.06
     fleece
    0.06
     WOM
    0.06
     εν
    0.06
     visite
    0.06
     쿠
    0.06
    Act Density 0.006%

    No Known Activations