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

    Neuronpedia

    INDEX
    Explanations

    catchy slogan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    르
    0.45
    錡
    0.45
    пр
    0.45
    लाइजेशन
    0.44
    াইয়
    0.44
     INE
    0.44
    वेळी
    0.43
     ჩატი
    0.43
     NAVIGATION
    0.43
     nome
    0.43
    POSITIVE LOGITS
     &&
    0.50
     Types
    0.43
     _______
    0.43
     এবং
    0.42
     ہتھی
    0.39
     和
    0.39
     ||
    0.38
     ট্র
    0.38
    コンパクト
    0.38
     desech
    0.38
    Act Density 0.010%

    No Known Activations