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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    体温
    -0.07
    慢
    -0.07
    .increment
    -0.07
    -alist
    -0.07
    速度
    -0.06
     Rank
    -0.06
    мор
    -0.06
     typ
    -0.06
     stag
    -0.06
     Cool
    -0.06
    POSITIVE LOGITS
    ellaneous
    0.08
    (gen
    0.08
     وفي
    0.07
    ={},
    0.07
     crear
    0.07
    开展
    0.07
    젛
    0.07
    🌈
    0.07
     وعلى
    0.07
     başlayan
    0.07
    Act Density 0.074%

    No Known Activations