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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     качестве
    -0.06
    řev
    -0.06
     unsustainable
    -0.06
     vå
    -0.06
     AG
    -0.06
     prostoru
    -0.06
    \AppData
    -0.06
    .That
    -0.06
     هر
    -0.06
     mange
    -0.06
    POSITIVE LOGITS
    (layers
    0.07
    xEA
    0.07
    650
    0.07
    icken
    0.06
    同时
    0.06
    旁
    0.06
     worker
    0.06
     ハ
    0.06
    STONE
    0.06
     Backbone
    0.06
    Act Density 0.000%

    No Known Activations