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

    Neuronpedia

    INDEX
    Explanations

    available

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cannot
    -0.08
     toxins
    -0.08
    mıştır
    -0.07
    新基建
    -0.07
    _context
    -0.07
    再一次
    -0.07
    iteral
    -0.07
     comfort
    -0.07
     alma
    -0.07
    旅游景区
    -0.07
    POSITIVE LOGITS
     hearings
    0.08
    饔
    0.07
    처리
    0.07
    开来
    0.07
    瀱
    0.07
     parl
    0.07
    ,f
    0.06
    صال
    0.06
    المع
    0.06
     Mounted
    0.06
    Act Density 0.004%

    No Known Activations