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

    Neuronpedia

    INDEX
    Explanations

    listing or role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     естественно
    0.56
     unfortunate
    0.56
    Historically
    0.56
     regrettable
    0.55
    Примеча
    0.54
     candidacy
    0.53
     দেড়
    0.53
    Unfortunately
    0.52
     leftover
    0.52
     dogma
    0.52
    POSITIVE LOGITS
     या
    0.57
     또는
    0.57
     或
    0.55
     hoặc
    0.54
     અથવા
    0.53
     ಅಥವಾ
    0.53
     किंवा
    0.51
    oran
    0.51
    及其
    0.51
     หรือ
    0.48
    Act Density 0.000%

    No Known Activations