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

    Neuronpedia

    INDEX
    Explanations

    DB

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     усл
    -0.08
    els
    -0.07
    _Select
    -0.07
     curse
    -0.07
    싴
    -0.07
    闻
    -0.07
    岳阳
    -0.07
    pose
    -0.07
    雕刻
    -0.06
     =
↵
    -0.06
    POSITIVE LOGITS
     stehen
    0.07
     headers
    0.07
    溲
    0.07
     bund
    0.07
     fluct
    0.07
    (theme
    0.06
     parentId
    0.06
     ситу
    0.06
     Moder
    0.06
    кат
    0.06
    Act Density 0.000%

    No Known Activations