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

    Neuronpedia

    INDEX
    Explanations

    code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    els
    0.38
     ধরা
    0.38
    ike
    0.38
    entu
    0.37
     exempel
    0.37
     tr
    0.36
     math
    0.36
     pesante
    0.36
    شت
    0.36
     little
    0.36
    POSITIVE LOGITS
     Sincerely
    0.57
     prodotti
    0.54
     sincerely
    0.54
    秉
    0.54
     proizvoda
    0.53
     produkty
    0.53
     চীন
    0.51
     productos
    0.50
     అధ్యక్షుడు
    0.49
     चीन
    0.49
    Act Density 0.000%

    No Known Activations