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

    Neuronpedia

    INDEX
    Explanations

    how follows common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     how
    1.77
    如何
    1.58
     cómo
    1.48
    how
    1.45
     कैसे
    1.45
    どのように
    1.44
    如何在
    1.40
     কীভাবে
    1.39
     কিভাবে
    1.38
    怎样
    1.38
    POSITIVE LOGITS
    ஹ
    0.41
    હ
    0.38
    ám
    0.36
    хо
    0.35
    ρού
    0.35
    áu
    0.35
    হ
    0.35
    aborasi
    0.34
    ัญ
    0.34
     hod
    0.33
    Act Density 0.061%

    No Known Activations