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

    Neuronpedia

    INDEX
    Explanations

    specific phrases and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UIntValue
    0.25
    CUDA
    0.23
    ウター
    0.22
     finalText
    0.21
    介绍了
    0.21
    洖
    0.21
     মিথ্যা
    0.21
    '>"+
    0.21
    动脉
    0.20
    翻译
    0.20
    POSITIVE LOGITS
     (
    0.35
     spezielle
    0.30
     appunto
    0.30
     tzv
    0.29
     tzw
    0.29
     específicos
    0.27
     user
    0.26
     colloqu
    0.26
     komfort
    0.26
     informally
    0.26
    Act Density 0.733%

    No Known Activations