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

    Neuronpedia

    INDEX
    Explanations

    Summaries and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boxShadow
    -0.07
    ateria
    -0.07
     trấn
    -0.07
    .outer
    -0.06
    Carrier
    -0.06
    cms
    -0.06
     उस
    -0.06
    др
    -0.06
     мая
    -0.06
     Кам
    -0.06
    POSITIVE LOGITS
    BF
    0.06
    ManagerInterface
    0.06
     heapq
    0.06
    HashCode
    0.06
    topl
    0.06
    ратег
    0.06
     Sic
    0.06
     skuteč
    0.05
    (edges
    0.05
    слов
    0.05
    Act Density 0.023%

    No Known Activations