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

    Neuronpedia

    INDEX
    Explanations

    street names and road types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Сто
    1.07
    i
    1.06
    кові
    0.99
     μεταξύ
    0.93
    を開催
    0.93
     Refs
    0.93
    J
    0.93
    iunea
    0.92
    u
    0.92
    و
    0.91
    POSITIVE LOGITS
    ä
    0.99
    يل
    0.95
    '{
    0.95
    ene
    0.94
    ながら
    0.93
     astute
    0.92
    та
    0.91
     defendant
    0.91
    itt
    0.91
     passionate
    0.90
    Act Density 0.023%

    No Known Activations