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

    Neuronpedia

    INDEX
    Explanations

    URLs and foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ଚ
    0.36
    Seat
    0.35
    FK
    0.35
     conta
    0.34
    갈
    0.33
    াসন
    0.33
    Sums
    0.32
    elleen
    0.32
     कोच
    0.32
     seat
    0.32
    POSITIVE LOGITS
     ചെയ്യുന്ന
    0.34
     அடிப்படையில்
    0.31
     عمل
    0.31
     hybridization
    0.31
     Byzant
    0.30
     만드는
    0.30
     ゙
    0.29
     мяг
    0.29
     istanbul
    0.29
     Stunde
    0.29
    Act Density 0.002%

    No Known Activations