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

    Neuronpedia

    INDEX
    Explanations

    legal representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    1.22
     an
    1.04
     I
    1.00
    ون
    0.97
    什么样的
    0.90
    :
    0.90
    in
    0.89
     R
    0.85
    ast
    0.85
    "
    0.85
    POSITIVE LOGITS
    ری
    1.38
    де
    1.22
    า
    1.10
    ン
    1.04
    ിയ
    0.99
    ای
    0.98
     سایټ
    0.96
     nodos
    0.96
    اوی
    0.95
    льный
    0.92
    Act Density 0.003%

    No Known Activations