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

    Neuronpedia

    INDEX
    Explanations

    economic inflation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     रीजन
    0.43
    頹
    0.42
     trotz
    0.42
     सेकेंडरी
    0.42
     bleed
    0.41
     zweite
    0.41
     terceiro
    0.41
    𝙛
    0.41
     அடுத்த
    0.40
     क्रमश
    0.40
    POSITIVE LOGITS
    एल
    0.42
     índices
    0.41
    ляем
    0.39
    mW
    0.38
    સ્ક
    0.38
    EL
    0.38
    ηγ
    0.38
    ELTS
    0.37
    UTF
    0.37
     দূর
    0.37
    Act Density 0.018%

    No Known Activations