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

    Neuronpedia

    INDEX
    Explanations

    default

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ků
    -0.07
    ohana
    -0.06
     آدم
    -0.06
    Mbps
    -0.06
    Assertions
    -0.06
     productService
    -0.06
    orsi
    -0.06
    ΟΤ
    -0.06
    .Payload
    -0.06
     blk
    -0.06
    POSITIVE LOGITS
    _refs
    0.06
     воздуха
    0.06
     över
    0.06
     misma
    0.06
    (screen
    0.06
    ",$
    0.06
    가지
    0.06
     shaved
    0.06
     mutate
    0.06
     semua
    0.06
    Act Density 0.002%

    No Known Activations