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

    Neuronpedia

    INDEX
    Explanations

    LaTeX pronunciation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hanya
    0.55
    ใหญ่
    0.53
    พาะ
    0.52
     সবসময়
    0.51
    ஸ்ட்
    0.51
    ატ
    0.51
    숍
    0.51
     बावजूद
    0.51
    ție
    0.49
     entlang
    0.49
    POSITIVE LOGITS
     ou
    0.61
     или
    0.58
     or
    0.52
     word
    0.51
    word
    0.50
    achos
    0.47
    ോട്ട
    0.46
     drain
    0.45
     ili
    0.45
    ims
    0.44
    Act Density 0.001%

    No Known Activations