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

    Neuronpedia

    INDEX
    Explanations

    C++ include statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     água
    0.55
     أما
    0.55
    تق
    0.51
     accueille
    0.50
    InBackground
    0.49
    िक
    0.48
     petróleo
    0.48
     لاءِ
    0.48
     eleições
    0.46
    طي
    0.45
    POSITIVE LOGITS
    Q
    0.56
          
    0.49
    es
    0.48
    i
    0.48
    л
    0.47
    "
    0.47
    ↵
    0.46
    新
    0.46
                 
    0.44
    关于
    0.44
    Act Density 0.014%

    No Known Activations