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

    Neuronpedia

    INDEX
    Explanations

    Ms. Ito

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     souris
    0.51
    款
    0.50
    ﻜ
    0.50
     brillant
    0.49
     éventuellement
    0.48
     গ্রেপ্ত
    0.48
     naszych
    0.47
    优雅
    0.47
     nossos
    0.46
     kisah
    0.46
    POSITIVE LOGITS
    ate
    0.49
     җи
    0.47
    de
    0.46
    den
    0.46
    certain
    0.46
     ܗ
    0.44
    ge
    0.43
    ger
    0.42
    uan
    0.42
    ors
    0.42
    Act Density 0.015%

    No Known Activations